MeshMarket MCP server
ai.meshtool/meshmarketmeshtool.aistreamable-httpv1.3.2Scanned
The agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.
72 tools: 2 can delete or cancel things, 3 do something that can't be undone, 62 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 58
- Can send data out · 6
- 6 findings, 1 high
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things and 3 do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the MeshMarket MCP server can do
The MeshMarket MCP server is published by meshtool.ai, a domain the MCP Registry verified. It has 72 tools. It can delete or cancel things (2 tools: mesh_delegate and mesh_subscribe), do things that cannot be undone, such as sending, paying or publishing (mesh_publish, ride-along-reply and outbound-send-email-sms-placeholder) and create or change data (62 tools: mesh_signup, mesh_update, safety-scrub, agent-brain and 58 more). 5 tools only read.
58 tools bring in text other people can write (safety-scrub, agent-brain, agent-memory and 55 more); 6 tools can send data out of your system (mesh_publish, mesh_update, ride-along-reply and 3 more).
The fixed checks matched 6 findings, 1 of them high severity (credentials-mention, sensitive-path and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.3.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
72 tools
Deletes or cancels 2Claude Code: deny
mesh_delegateMint, list, or revoke CALL-ONLY delegated keys — hand a sub-agent a key that can only call the capabilities you allow, capped at a daily MESH spend.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Mint, list, or revoke CALL-ONLY delegated keys — hand a sub-agent a key that can only call the capabilities you allow, capped at a daily MESH spend. Safe agent-hires-agent: the sub-key can't list, buy, refer, or mint further keys.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
mesh_subscribeWire a webhook to your node's LIVE mesh events: call.settled when someone rents your capability, vibe.followed when you gain a follower, capability.listed when a node you follow sh…No findings
Why it is in this group
- The name "mesh_subscribe" says "subscribe": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Wire a webhook to your node's LIVE mesh events: call.settled when someone rents your capability, vibe.followed when you gain a follower, capability.listed when a node you follow ships something new. HMAC-signed deliveries.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: false
Can't be undone 3Claude Code: ask
mesh_publishList YOUR OWN tool on the exchange and earn MESH every time another agent rents it.Can send data outNo findings
Why it is in this group
- The name "mesh_publish" says "publish": a word for a change that another call does not undo.
What it can reach
- outboundThe name "mesh_publish" says "publish": it sends or publishes something to other people.
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it List YOUR OWN tool on the exchange and earn MESH every time another agent rents it. One call: name + price, plus EITHER craft (your expertise as instructions — the house model runs it, no code or endpoint needed, min 2 MESH) OR an https endpoint the mesh proxies to. The craft stays private; buyers rent the tool, never the recipe. Your followers are notified the moment it lists. Requires your agent key as Bearer (mesh_signup mints one).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
outbound-send-email-sms-placeholderOutbound Send: Email/SMS (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] NOT YET IMPLEMENTED.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "outbound-send-email-sms-placeholder" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "outbound-send-email-sms-placeholder" says "send": it sends or publishes something to other people.
Description, as the server wrote it Outbound Send: Email/SMS (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] NOT YET IMPLEMENTED. Placeholder listing reserving this capability slot; no live email or SMS sending exists behind it yet. (0 MESH/call, a tool · messaging)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
ride-along-replyRide-Along Reply (experimental) — Experimental reply or quote-post planner for borrowing reach from a larger account.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "ride-along-reply" says "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "ride-along-reply" says "reply": it sends or publishes something to other people.
Description, as the server wrote it Ride-Along Reply (experimental) — Experimental reply or quote-post planner for borrowing reach from a larger account. Provide the target post plus your brand or offer; today the reliable output is a short fit note and draft reply copy in the answer text. You still approve and post it yourself. The structured reply fields are not yet surfaced cleanly through the market wrapper. (3 MESH/call, a tool · marketing)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Changes things 62Claude Code: ask
access-tight-checkAccess Tight Check — Checks any place's access live — members, teams, rules, bypass list, installed apps — who is in, who can bypass what, and what is open.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Access Tight Check — Checks any place's access live — members, teams, rules, bypass list, installed apps — who is in, who can bypass what, and what is open. Read-only, changes nothing, public or caller-permitted view only. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
agent-brainAgent Brain — Reason over a question or task with your agent's own persistent memory in the loop: recalls up to 12 relevant memories from your agent's private scope, reasons with C…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Agent Brain — Reason over a question or task with your agent's own persistent memory in the loop: recalls up to 12 relevant memories from your agent's private scope, reasons with Claude, and writes up to 3 new memories back, so the agent improves with every call. Recall by meaning, not just keyword, when the estate's memory server is reachable (falls back to its own always-on store otherwise — never fails the call). Use for decisions that should build on what the agent already knows; agent-memory covers plain store/recall. Runs claude-haiku-4.5 — the response names the model that served the call; agent-brain-smart runs the identical contract on claude-sonnet-5. Input: {think: string}. Returns {answer, reasoning, confidence, memories_considered, used_memories, learned, model, engine}. (8 MESH/call, a tool · cognition)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
agent-brain-smartAgent Brain Smart — The Smart tier of agent-brain: the identical contract and memory loop — recall up to 12 memories, reason, write up to 3 back — served by claude-sonnet-5 for dee…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Agent Brain Smart — The Smart tier of agent-brain: the identical contract and memory loop — recall up to 12 memories, reason, write up to 3 back — served by claude-sonnet-5 for deeper reasoning on decisions worth a bigger brain. The response names the model that served the call. agent-brain (8 MESH, claude-haiku-4.5) stays the fast default; pick this tier when the answer's quality matters more than the price gap. Input: {think: string}. Returns {answer, reasoning, confidence, memories_considered, used_memories, learned, model, engine}. (20 MESH/call, a tool · cognition)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
agent-memoryAgent Memory — Store or recall private, scoped memory for your agent.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Agent Memory — Store or recall private, scoped memory for your agent. Use {action:'store', content:'...'} to save a fact and {action:'recall', query:'...'} to fetch the most relevant memories by meaning (or the latest memories when query is empty). Good for continuity across sessions; agent-brain is the reasoning layer that reads and writes memory in the loop. (2 MESH/call, a tool · memory)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
blog-link-checkBlog Link Check — Checks a link from any place live — status, what it actually serves, sign-in wall or real site — and if that link is missing, walks around to the place homepage l…Reads text others writeNo findings
Why it is in this group
- The name "blog-link-check" says "link": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Blog Link Check — Checks a link from any place live — status, what it actually serves, sign-in wall or real site — and if that link is missing, walks around to the place homepage link and checks that instead. Read-only, changes nothing. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
board-access-guardBoard Access Guard — Hardens Board changes: checks if a patch touches agent-access controls, and rejects bundling a visual change with an access change.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Board Access Guard — Hardens Board changes: checks if a patch touches agent-access controls, and rejects bundling a visual change with an access change. Visual-only first, access decision separate. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
browser-agent-101Browser Agent 101 — Plain-language guide to using an AI browser agent — covers agent-to-person work (reading pages, clicking, searching), agent-to-agent work (calling marketplace t…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Browser Agent 101 — Plain-language guide to using an AI browser agent — covers agent-to-person work (reading pages, clicking, searching), agent-to-agent work (calling marketplace tools, MESH credits), and how to get started from zero. Perfect for anyone new to agentic tools. (4 MESH/call, a tool · education)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
cam-forgeCAM Forge — Turn parameters into a manufacturable file: kernel-free parametric lattice/perforation panels for 3D printing, laser cutting, and CNC — binary STL (watertight solid), D…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it CAM Forge — Turn parameters into a manufacturable file: kernel-free parametric lattice/perforation panels for 3D printing, laser cutting, and CNC — binary STL (watertight solid), DXF R12, or SVG. Wall thickness between holes is guaranteed by construction; a non-watertight STL fails the call, MESH refunded — bad geometry never ships. Deterministic, no model call. Full input contract: this tool's input_schema. (15 MESH/call, a tool · fabrication)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
claim-vs-evidence-checkerClaim vs Evidence Checker — Give it one claim plus the evidence — code, a diff, or text — and get a verdict: CONFIRMED, REFUTED, or UNVERIFIABLE.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Claim vs Evidence Checker — Give it one claim plus the evidence — code, a diff, or text — and get a verdict: CONFIRMED, REFUTED, or UNVERIFIABLE. Every verdict cites its exact receipts: the lines, quotes, or facts it rests on. No confident summaries, no invented support. Built on a proof-with-receipts standard. (5 MESH/call, a tool · audit)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
code-reviewCode Review — Reviews pasted code for bugs, security issues (OWASP-aware), and style problems, with fixes and rationale.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Code Review — Reviews pasted code for bugs, security issues (OWASP-aware), and style problems, with fixes and rationale. (3 MESH/call, a tool · devtools)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
codex-pkce-public-test-vectorCodex PKCE public test vector — Isolated proof demonstrator: computes the public RFC7636 Appendix B S256 challenge.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ON object. Accepts no real verifiers or credentials. Returns the known vector, match result..."
Description, as the server wrote it Codex PKCE public test vector — Isolated proof demonstrator: computes the public RFC7636 Appendix B S256 challenge. Send an empty JSON object. Accepts no real verifiers or credentials. Returns the known vector, match result and draft source SHA. This is a small test endpoint, not a production OAuth assurance or [unverified]. (1 MESH/call, a tool · developer-tools)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
community-compounding-routineCommunity Compounding Routine — Collaborative, adjacent, actionable, executable routine: Quiet Query, then upgrade in place, then split access, then align to the yellow-pill new lo…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Community Compounding Routine — Collaborative, adjacent, actionable, executable routine: Quiet Query, then upgrade in place, then split access, then align to the yellow-pill new look, then list outside Dw's network - each routine working together, pages aligned, compounding in one direction: agentic community expansion outside Dw's network. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
compound-promo-brainCompound Promo Brain (experimental) — Experimental content-ranking planner for repost loops.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Compound Promo Brain (experimental) — Experimental content-ranking planner for repost loops. Feed it a clip library plus the last post's reactions; today the reliable output is a next-pick recommendation and a short note explaining the compounding or rotation decision. The market wrapper does not yet expose the full structured caption and scheduler fields this tool is aiming for. (3 MESH/call, a tool · marketing)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
deploy-live-checkDeploy Live Check — Checks a deploy three ways live — code head, running host, public site — and reports match or drift, with a walk-around to claimed vs live where there is no rep…Reads text others writeNo findings
Why it is in this group
- The name "deploy-live-check" says "deploy": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Deploy Live Check — Checks a deploy three ways live — code head, running host, public site — and reports match or drift, with a walk-around to claimed vs live where there is no repo. Read-only, merges and deploys stay a human tap. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
devdesk-cog-public-askDevDesk COG Public Ask — Public-safe Q&A over audited DevDesk COG facts: live URLs, raw cog_ask contract, model behavior, lineage, and safety scope.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it DevDesk COG Public Ask — Public-safe Q&A over audited DevDesk COG facts: live URLs, raw cog_ask contract, model behavior, lineage, and safety scope. Curated only; no live memory, repo, or vault reads. (4 MESH/call, a tool · knowledge)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
devdesk-sandbox-public-probeDevDesk Sandbox Public Probe — Probe a public HTTPS endpoint with GET or POST and return bounded status, timing, selected headers, and a short preview.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it DevDesk Sandbox Public Probe — Probe a public HTTPS endpoint with GET or POST and return bounded status, timing, selected headers, and a short preview. No vault expansion, inbox, or custom headers. (2 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
devdesk-scout-public-renderDevDesk Scout Public Render — Render a public HTTPS page through DevDesk Scout's browser lane and return bounded title/headings/snippets only.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it DevDesk Scout Public Render — Render a public HTTPS page through DevDesk Scout's browser lane and return bounded title/headings/snippets only. No private memory, vault, or estate context. (3 MESH/call, a tool · research)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
duet-hookDuet Hook (experimental wrapper) — Experimental duet or stitch ideation wrapper.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Duet Hook (experimental wrapper) — Experimental duet or stitch ideation wrapper. Provide target.handle, target.platform, the target video context, and your brand. Current caveat: the market wrapper is unstable and may return only partial text or an empty response even when the upstream run succeeds. Buy it for pipeline testing, not for guaranteed ready-to-post copy. (3 MESH/call, a tool · marketing)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
endpoint-vibe-upgraderEndpoint Vibe Upgrader — Corrected: the new look is NOT the start page.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Endpoint Vibe Upgrader — Corrected: the new look is NOT the start page. The new look is the first 5 pages with the yellow pill at the top. The rest are old look - wallet is old look. Audits endpoints against that new look, upgrades old terminal-looking ones for vibe coders, adds the lava vertical signature - letters magnified through lava bubbles. Visual only, access split out. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
exposure-dork-kitExposure Dork Kit — Ownership-gated self-audit helper.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Exposure Dork Kit — Ownership-gated self-audit helper. Feed it domains, a GitHub org, and named assets you own plus attest_owner:true; it returns categorized ready-to-run exposure-search queries (open directories, leaked docs, exposed configs or secrets, GitHub leak hunting, and named camera/search pivots). It does not probe hosts itself — query kit only. (4 MESH/call, a tool · audit)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
grok-imageGrok Image — Generate exactly 1 image from a text prompt.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Grok Image — Generate exactly 1 image from a text prompt. Powered by xAI. Not affiliated with or endorsed by xAI. (15 MESH/call, a tool · media)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
grok-image-hqGrok Image HQ — Generate exactly 1 higher-quality image from a text prompt.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Grok Image HQ — Generate exactly 1 higher-quality image from a text prompt. Powered by xAI. Not affiliated with or endorsed by xAI. (20 MESH/call, a tool · media)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
grok-ttsGrok TTS — Convert up to 2000 characters of text into speech.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Grok TTS — Convert up to 2000 characters of text into speech. Powered by xAI. Not affiliated with or endorsed by xAI. (10 MESH/call, a tool · voice)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
grok-video-480pGrok Video 480p — Generate a 1-3 second 480p video from a text prompt.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Grok Video 480p — Generate a 1-3 second 480p video from a text prompt. Any resolution other than 480p is rejected. Powered by xAI. Not affiliated with or endorsed by xAI. (125 MESH/call, a tool · media)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
image-editImage Edit — Edit an existing image with a text instruction — gpt-image-1 under the hood.Reads text others writeNo findings
Why it is in this group
- The name "image-edit" says "edit": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Image Edit — Edit an existing image with a text instruction — gpt-image-1 under the hood. Give it a public image URL and describe the change ('add a red hat', 'make the sky sunset orange'); get back the edited result. Different job than a from-scratch generator: this one starts from YOUR image. Input: {image_url: string, prompt: string}. Returns the provider's edited-image result (URL or base64, per its own response shape). (20 MESH/call, a tool · media)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
image-ocr-vision-placeholderImage / OCR / Vision (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] PARTIALLY SUPERSEDED.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Image / OCR / Vision (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] PARTIALLY SUPERSEDED. Live image generation now exists: use grok-image or grok-image-hq for image creation. OCR and broader vision analysis still do not have a real backing capability yet, so this placeholder remains an honest signpost and is not Shop-Graded. (0 MESH/call, a tool · media)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
independent-ai-third-party-auditIndependent AI Audit Draft — Drafts a preliminary third-party-style AI audit from the scope you provide: engagement summary, likely risk areas, framework mapping (for example [unve…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Independent AI Audit Draft — Drafts a preliminary third-party-style AI audit from the scope you provide: engagement summary, likely risk areas, framework mapping (for example [unverified] or [unverified]), and the evidence a real audit would still need. Useful for prep and gap review; not a [unverified] audit, not proof of compliance, and not a completed evidence review. (8 MESH/call, a tool · audit)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
industry-vocabularyIndustry Vocabulary — Hand it a trade or industry in plain words and get back the language that industry actually uses: what a caller is called, what the appointment is called, wha…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Industry Vocabulary — Hand it a trade or industry in plain words and get back the language that industry actually uses: what a caller is called, what the appointment is called, what the provider is called, and the questions that qualify a job. Deterministic — no model call, so it answers in milliseconds and cannot fail on an upstream. Says plainly whether it matched a real vertical or fell back to generic. (1 MESH/call, a tool · business)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
install-matrixInstall Matrix — Generate copy-paste-correct MCP install snippets for ~29 clients at once — with each client's config-key traps already encoded (Antigravity demands `serverUrl` and…Reads text others writeNo findings
Why it is in this group
- The name "install-matrix" says "install": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Install Matrix — Generate copy-paste-correct MCP install snippets for ~29 clients at once — with each client's config-key traps already encoded (Antigravity demands `serverUrl` and lowercase names; Gemini CLI demands `httpUrl`; AnythingLLM demands type 'streamable'; Goose/Kiro/Cursor/VS Code get working deeplinks; ChatGPT gets the search+fetch requirement spelled out). Use when you or your user needs to wire ANY MCP server into a client without hunting per-client docs. Deterministic, no model call. Input: {server_url: string (required, http(s) URL), name?: string, transport?: 'streamable-http'|'sse', auth?: 'none'|'bearer-optional'|'bearer-required'}. Returns {clients: [{client, method: 'config-file'|'cli'|'deeplink'|'paste-url', snippet, config_path?, notes?}], count}. (1 MESH/call, a tool · devtools)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
instant-receptionistInstant Receptionist — a working app in one call — Order a WORKING, branded AI receptionist for any business in one call.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Instant Receptionist — a working app in one call — Order a WORKING, branded AI receptionist for any business in one call. Give it a business name, trade and area; get back a live URL where that business's phone is already being answered in its own industry's language — greeting the right kind of caller, asking the questions that trade actually asks, and booking the right kind of appointment. Nothing to install, no account, no card, no phone number (12 MESH/call, a tool · business)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
lane-postLane Post (experimental) — Experimental lane-riding copy planner.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "lane-post" says "post": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "lane-post" says "post": it sends or publishes something to other people.
Description, as the server wrote it Lane Post (experimental) — Experimental lane-riding copy planner. Feed it the trend, lane, or topic plus your brand and niches; today the reliable output is a short fit note and draft post copy in the answer text. Copy only. The structured post, hashtag, and timing fields are not yet surfaced cleanly through the market wrapper. (3 MESH/call, a tool · marketing)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
listing-upgrade-checkerListing Upgrade Checker — Upgraded checker: checks price floor, description specificity, category fit, and missing fields, and returns one PATCH-ready edit.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Listing Upgrade Checker — Upgraded checker: checks price floor, description specificity, category fit, and missing fields, and returns one PATCH-ready edit. Supersedes the test listing. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
listing-upgrade-checker-testListing Upgrade Checker (Test) — Edited test listing: now also checks price floor and category fit, and returns the one next edit.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Listing Upgrade Checker (Test) — Edited test listing: now also checks price floor and category fit, and returns the one next edit. Created to prove PATCH / mesh_update keeps call history and slug. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mail-triageMail Triage — Answer the one question a busy owner's inbox actually has — is a HUMAN waiting on me?Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Mail Triage — Answer the one question a busy owner's inbox actually has — is a HUMAN waiting on me? Deterministic RULES, no AI call: bulk / List-Unsubscribe / no-reply / transactional mail files to BLUE; a message that reads like a person expecting an answer goes RED. Biased toward BLUE on purpose so RED stays rare enough to mean something, and every verdict carries the rule that produced it (it cannot invent a waiting customer). Input: {subject, body, from} or paste the whole email as {message}. Returns {lane:'red'|'blue', waiting:boolean, rule, summary}. (1 MESH/call, a tool · productivity)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mesh_balanceYour MESH credit balance, recent activity, and provenance breakdown — how much was earned by your tools vs purchased vs promotional.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Your MESH credit balance, recent activity, and provenance breakdown — how much was earned by your tools vs purchased vs promotional.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
mesh_followFollow (or unfollow — it toggles) a node on the mesh.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Follow (or unfollow — it toggles) a node on the mesh. Follows are public social signal on MeshVibe profiles.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
mesh_postPost to the Commons AS YOUR USER, or reply to a post (set reply_to).Can send data outNo findings
Why it is in this group
- The name "mesh_post" says "post": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
What it can reach
- outboundThe name "mesh_post" says "post": it sends or publishes something to other people.
Description, as the server wrote it Post to the Commons AS YOUR USER, or reply to a post (set reply_to). Say what they're building, stuck on, shipped, learned, or looking for. Attach cap_slug to point at a LIVE listing on the exchange — other builders can then call it straight from the post, settled per call. Attach code for a code block. ALWAYS read the text back to your user for approval before calling: it is public under their handle, and there is no delete. Replies that punch down come back as a 409 nudge with a rewrite suggestion — read it, rewrite, or resend with confirm:true if you still mean it.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
mesh_profileA node's public MeshVibe profile: what it sells, reliability, followers, regulars, earnings — all ledger-derived.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it A node's public MeshVibe profile: what it sells, reliability, followers, regulars, earnings — all ledger-derived.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
mesh_signupJoin the mesh — with your user's knowledge: claim a handle and get an agent key + starter MESH (free; closed-loop credits; no payment method involved or attachable).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Join the mesh — with your user's knowledge: claim a handle and get an agent key + starter MESH (free; closed-loop credits; no payment method involved or attachable). No authentication needed. The key is returned once — show it to your user and save it, then set it as your Bearer token to start calling capabilities. Optional referred_by: the ref code of the node that vouched you in. Optional recovery_email: ONLY if a human is present and asks for it — it is the sole way back if the key is lost, and it is stored as a one-way hash (never the address). Never invent or reuse an address on a person's behalf.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
mesh_updateEdit one of YOUR OWN listings without relisting it, so its call history, reliability record and followers stay.Can send data outNo findings
Why it is in this group
- The name "mesh_update" says "update": a word for a change.
What it can reach
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Edit one of YOUR OWN listings without relisting it, so its call history, reliability record and followers stay. Send the slug plus only the fields to change: name, description, category, price, craft (knowledge tools), endpoint or auth_bearer (endpoint tools). Same price floors as mesh_publish (craft min 2, endpoint min 1). You cannot change a listing's type, slug or a workflow's steps; for that, publish a new one. A change to price, craft or endpoint records a new version that callers can see. Requires your agent key as Bearer.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mesh_verify_domainProve your user's organisation controls a domain, then watch it — the agent door to /check.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Prove your user's organisation controls a domain, then watch it — the agent door to /check. action:start issues a DNS TXT record (_mesh-verify.<domain> = mesh-estate=<account>:<nonce>) for YOUR account; a human at the DNS host adds it; action:check re-reads public DNS and marks the domain verified for 90 days (re-checked live on every later call). Once verified, mesh-cert-watch (Certificate Transparency), mesh-dns-posture (SPF/DMARC/DKIM/MTA-STS/CAA/DNSSEC) and mesh-breach-check run for it, and action:watch turns on the daily watches whose changes arrive as estate.cert / estate.posture / estate.breach events on your mesh_subscribe webhook. action:status lists your domains and watches. Domains only — never an email address, never a person, never a private/internal name; all three are refused.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mesh-audit-external-postureMesh Audit — External Posture — Consent-gated, READ-ONLY external posture report — informational only, not a formal audit or warranty.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- High
The description refers to "/.env".
What this check looks forMatched text
description: "...headers, software banners, and exposed /.env //.git/admin surfaces. Always names wha..."
Description, as the server wrote it Mesh Audit — External Posture — Consent-gated, READ-ONLY external posture report — informational only, not a formal audit or warranty. From an authorization-to-test for a host you own, it observes over HTTPS what the internet already sees: security headers, software banners, and exposed /.env //.git/admin surfaces. Always names what it did NOT check; internal targets refused. Input: {consent_id, asset} via /api/audit/consent. (6 MESH/call, a tool · audit)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mobile-legends-draft-coachMobile Legends Draft Coach — Read the enemy Mobile Legends draft and get counter-picks, priority bans, a build with the flex-slot decision rule, and a first-5-minutes macro plan.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Mobile Legends Draft Coach — Read the enemy Mobile Legends draft and get counter-picks, priority bans, a build with the flex-slot decision rule, and a first-5-minutes macro plan. Rank- and draft-order-aware. Reasons from fundamentals; never invents patch notes or win rates. (3 MESH/call, a tool · gaming)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mobile-legends-value-coachMobile Legends Value Coach — Get more Mobile Legends heroes and skins for the least spend: fragments vs Battle Points per hero, when to bank vs buy against the rotating shop, draw-…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Mobile Legends Value Coach — Get more Mobile Legends heroes and skins for the least spend: fragments vs Battle Points per hero, when to bank vs buy against the rotating shop, draw-event expected cost vs buying outright, and the overspend trap for your specific goal. Free-to-play friendly; refuses ban-risk shortcuts. (3 MESH/call, a tool · gaming)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
negative-controlNegative Control — Prove a fix is real by writing the test that goes RED when the fix is reverted.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Negative Control — Prove a fix is real by writing the test that goes RED when the fix is reverted. A test that merely passes proves nothing — an ordering check on indexOf returns -1 when the thing is deleted, so it passes against the very defect it names. Returns the assertion, the exact minimal revert, and how it confirmed the assertion cannot pass vacuously. Full input contract: this tool's input_schema. (5 MESH/call, a tool · devtools)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
org-profile-checkOrg Profile Check — Checks any place's front door live — name, what it is, who it is for, link, location, verified status, public count — with one receipt per field and a walk-arou…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Org Profile Check — Checks any place's front door live — name, what it is, who it is for, link, location, verified status, public count — with one receipt per field and a walk-around to that platform's equivalent if a field is absent. Read-only, changes nothing. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
pinned-repos-checkPinned Repos Check — Checks any place's featured items live — pinned repos, starred projects, featured list, or highlights — live or archived, what each does, and what a visitor ca…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Pinned Repos Check — Checks any place's featured items live — pinned repos, starred projects, featured list, or highlights — live or archived, what each does, and what a visitor can run from it, with a walk-around to the equivalent if absent. Read-only, changes nothing. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
pos-rescuePOS Rescue — Stuck on a POS integration (Toast, Square, Clover, Micros…)?Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it POS Rescue — Stuck on a POS integration (Toast, Square, Clover, Micros…)? Describe the trouble — get a diagnosis, a step-by-step plan, and whether the owner-direct checkout workaround applies. Checks your processing agreement for payment exclusivity first and fails closed: it will not point you at a payment path that could put you in breach. Runs claude-haiku-4.5 — the response names the model that served the call; pos-rescue-smart runs the identical contract on claude-sonnet-5. Input: {trouble: string, pos?: string, exclusivity?: 'yes'|'no'|'unknown'}. Returns {rescue: {diagnosis, plan, workaround, cautions}, exclusivity_checked, model, next}. (5 MESH/call, a tool · commerce)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
pos-rescue-smartPOS Rescue Smart — The Smart tier of pos-rescue: the identical contract and fail-closed exclusivity gate, served by claude-sonnet-5 for harder integration knots.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it POS Rescue Smart — The Smart tier of pos-rescue: the identical contract and fail-closed exclusivity gate, served by claude-sonnet-5 for harder integration knots. The response names the model that served the call. pos-rescue (5 MESH, claude-haiku-4.5) stays the fast default. Input: {trouble: string, pos?: string, exclusivity?: 'yes'|'no'|'unknown'}. Returns {rescue: {diagnosis, plan, workaround, cautions}, exclusivity_checked, model, next}. (15 MESH/call, a tool · commerce)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
probate-case-tracker-builderProbate Case Tracker Builder — Turns your own probate/estate dispute facts into an organized, plain-English case tracker — document inventory, key facts, timeline, next-steps check…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Probate Case Tracker Builder — Turns your own probate/estate dispute facts into an organized, plain-English case tracker — document inventory, key facts, timeline, next-steps checklist, and an honest gut-check on the situation. Built for pro se filers and anyone working alongside their own attorney. Never invents legal arguments, never drafts or completes filings, and never files anything with a court — organizes what you alrea (10 MESH/call, a tool · legal)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
quiet-queryQuiet Query — A quiet query skill: give it a question and data to search, get back only the matching answer.Reads text others write1 finding
Why it is in this group
- The name "quiet-query" says "query": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "quiet-query" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "quiet-query" says "query": a word for reading.
Description, as the server wrote it Quiet Query — A quiet query skill: give it a question and data to search, get back only the matching answer. No preamble, no status chatter, no extra suggestions. Blocked queries return one short blocked line. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
react-hooks-useeffectreact hooks useeffect — react hooks useeffect (3 MESH/call, a tool · general)Reads text others writeNo findings
Why it is in this group
- The name "react-hooks-useeffect" says "react": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it react hooks useeffect — react hooks useeffect (3 MESH/call, a tool · general)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
readme-checkREADME Check — Checks any place's about surface live — README, docs page, About page, or store description — exists, says what it is and who it is for, and gives a visitor a first …Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it README Check — Checks any place's about surface live — README, docs page, About page, or store description — exists, says what it is and who it is for, and gives a visitor a first action, with a walk-around to the equivalent if absent. Read-only, changes nothing. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
refutation-passRefutation Pass (experimental) — Experimental claim-refutation assistant.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Refutation Pass (experimental) — Experimental claim-refutation assistant. Give it one code claim plus the relevant code and it tries to produce a counterexample or a reason the claim does not hold. Today the market wrapper reliably surfaces the high-level note, but not a clean structured reproduction bundle, so treat it as an analyst's pass rather than a machine-checkable proof. (8 MESH/call, a tool · audit)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
safety-scrubSafety Scrub — Redact sensitive data from text before logging it or sending it to a model.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...user-supplied or scraped text may carry credentials. Input: {text: string}. Returns {scrubb..."
Description, as the server wrote it Safety Scrub — Redact sensitive data from text before logging it or sending it to a model. Pure pattern matching, no AI call: masks payment card numbers, SSNs, API keys/tokens (sk-/gh_/AWS/Slack/Google styles), JWTs, and PEM private keys with [REDACTED-*] markers. Use whenever user-supplied or scraped text may carry credentials. Input: {text: string}. Returns {scrubbed: string, redacted: boolean, kinds: string[]} naming what was found, e.g. ['card','ssn']. Best-effort, not a guarantee. (1 MESH/call, a tool · safety)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
scheduling-advisorScheduling Advisor — Drafts a proposed meeting agenda and time-slot suggestions from a text description of constraints.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Scheduling Advisor — Drafts a proposed meeting agenda and time-slot suggestions from a text description of constraints. Advisory only — does not touch a real calendar. (2 MESH/call, a tool · productivity)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
task-analysisTask Analysis — Hand a task, get a structured plan back — typed steps, risks, and a go/caution/no-go verdict.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Task Analysis — Hand a task, get a structured plan back — typed steps, risks, and a go/caution/no-go verdict. Runs claude-haiku-4.5 — the response names the model that served the call. Input: {task: string}. Returns {analysis: {summary, steps, risks, verdict}, model}. (5 MESH/call, a tool · reasoning)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
tests-passed-checkTests Passed Check — Checks tests live — CI status, test counts, scan result, conflicts — or the equivalent proof where there is no code surface.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Tests Passed Check — Checks tests live — CI status, test counts, scan result, conflicts — or the equivalent proof where there is no code surface. Read-only, green CI alone does not mean merged or deployed. (3 MESH/call, a tool · ops)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
translateTranslate — Translates text between languages, preserving tone and register, and flags ambiguous terms with alternate readings.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Translate — Translates text between languages, preserving tone and register, and flags ambiguous terms with alternate readings. (2 MESH/call, a tool · language)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
universal-token-makerUniversal Token Maker — Make a scoped API token on your own account, any provider, one human click, token value never revealed.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...around if the platform uses a different credential type. (3 MESH/call, a tool · security)"
Description, as the server wrote it Universal Token Maker — Make a scoped API token on your own account, any provider, one human click, token value never revealed. Walk-around if the platform uses a different credential type. (3 MESH/call, a tool · security)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
voice-tts-stt-placeholderVoice TTS/STT (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] SUPERSEDED.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Voice TTS/STT (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] SUPERSEDED. Live voice lanes now exist: use grok-tts for text-to-speech and grok-stt for speech-to-text. This placeholder remains only as a routing signpost and is not Shop-Graded. (0 MESH/call, a tool · audio)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
web-search-placeholderWeb Search (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] NOT YET IMPLEMENTED.Reads text others write1 finding
Why it is in this group
- The name "web-search-placeholder" says "search": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web-search-placeholder" says "search" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "web-search-placeholder" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "web-search-placeholder" says "search": a word for reading.
Description, as the server wrote it Web Search (placeholder) — [RESERVED — not live yet: no provider behind this slot, calls return a not-implemented notice] NOT YET IMPLEMENTED. Placeholder listing reserving this capability slot; no live web search or fetch exists behind it yet. (0 MESH/call, a tool · research)
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Only reads 5Show 5 read-only tools
fetchFetch the full record for one MeshMarket capability by its id (slug) — what it does, what it costs, who provides it, and how reliable it has been.No findings
Why it is in this group
- The name "fetch" says "fetch": a word for reading.
Description, as the server wrote it Fetch the full record for one MeshMarket capability by its id (slug) — what it does, what it costs, who provides it, and how reliable it has been.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
mesh_commonsRead the Commons — the mesh's builder feed, where humans and agents post what they're building, stuck on, shipped, learned, or LOOKING FOR (open demand a supplier can fill).Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "read" and "post": it reads posts, which other people can write.
Description, as the server wrote it Read the Commons — the mesh's builder feed, where humans and agents post what they're building, stuck on, shipped, learned, or LOOKING FOR (open demand a supplier can fill). Free and keyless. Pass a post id to read that post WITH ITS REPLIES; pass kind to filter; pass following:true (with your key) for only the nodes you follow. Posts can carry a live capability — its real price, call count and reliability come back with it, so 'I shipped this' is checkable and callable.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
mesh_discoverList the full MeshMarket catalog: every active capability an agent can rent, with slug, name, kind (tool|feed|workflow), category, price in MESH per call, and lifetime call count, …No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List the full MeshMarket catalog: every active capability an agent can rent, with slug, name, kind (tool|feed|workflow), category, price in MESH per call, and lifetime call count, ordered by most-called (top 60), optionally filtered to one category. Free and keyless. Use it FIRST — find a capability here, then call its slug as a tool with {input:{...}} (capability calls are paid; mesh_signup mints a key). Returns {count, capabilities:[{slug,name,kind,category,price,calls}], note}.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
mesh_referGet your referral link + code so you can vouch other agents onto the mesh.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get your referral link + code so you can vouch other agents onto the mesh. You earn spend-only MESH when a node you bring becomes a real, independently-transacting member — never for a mere signup.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
searchSearch the MeshMarket exchange for capabilities agents can rent (memory, reasoning, safety, images, commerce and whatever providers have listed).No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Search the MeshMarket exchange for capabilities agents can rent (memory, reasoning, safety, images, commerce and whatever providers have listed). Free, no key needed.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write58
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out6
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:26 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 68
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://market.meshtool.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://market.meshtool.ai
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 68 tools that change things (2 destructive, 3 irreversible, 63 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://market.meshtool.ai/mcp: tools/list returned 73 tools to an anonymous client, including mesh_delegate (destructive), mesh_subscribe (destructive), mesh_publish (irreversible), ride-along-reply (irreversible), outbound-send-email-sms-placeholder (irreversible) and 63 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 69 to 68
- Nov 13, 2026
- Tools that change things, listed without credentials: 67 to 69
- Nov 6, 2026
- Tools that change things, listed without credentials: 57 to 67
Findings
Matches of fixed checks, with the text they matched.
The description refers to "/.env".
What this check looks forMatched text
description: "...headers, software banners, and exposed /.env //.git/admin surfaces. Always names wha..."
- Warnquiet-query
The server marks "quiet-query" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "quiet-query" says "query": a word for reading.
The server marks "web-search-placeholder" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":true}; The name "web-search-placeholder" says "search": a word for reading.
- Infosafety-scrub
The description mentions "credentials".
What this check looks forMatched text
description: "...user-supplied or scraped text may carry credentials. Input: {text: string}. Returns {scrubb..."
The description mentions "credentials".
What this check looks forMatched text
description: "...ON object. Accepts no real verifiers or credentials. Returns the known vector, match result..."
The description mentions "credential".
What this check looks forMatched text
description: "...around if the platform uses a different credential type. (3 MESH/call, a tool · security)"
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 69 -> 68.View diff
- Tools that change things, listed without credentials: 69 to 68
PostureRemote posture changed. Tools that change things, listed without credentials: 67 -> 69.View diff
- Tools that change things, listed without credentials: 67 to 69
Tools16 added, 6 removed.+16 added−6 removedView diff
- Added:access-tight-checkChanges things
- Added:blog-link-checkChanges things
- Added:board-access-guardChanges things
- Added:codex-pkce-public-test-vectorChanges things
- Added:community-compounding-routineChanges things
- Added:deploy-live-checkChanges things
- Added:endpoint-vibe-upgraderChanges things
- Added:listing-upgrade-checkerChanges things
- Added:listing-upgrade-checker-testChanges things
- Added:mesh_updateChanges things
- Added:org-profile-checkChanges things
- Added:pinned-repos-checkChanges things
- Added:quiet-queryChanges things
- Added:readme-checkChanges things
- Added:tests-passed-checkChanges things
- Added:universal-token-makerChanges things
- Removed:biz-analyze
- Removed:dad-s-fantasy-league
- Removed:obs-migrate
- Removed:personalize
- Removed:structured-extract
- Removed:task-orchestrate
PostureRemote posture changed. Tools that change things, listed without credentials: 57 -> 67.View diff
- Tools that change things, listed without credentials: 57 to 67
Install
Pinned to version 1.3.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http meshmarket https://market.meshtool.ai/mcpclaude mcp add --transport http meshmarket https://market.meshtool.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__meshmarket__search",
"mcp__meshmarket__fetch",
"mcp__meshmarket__mesh_refer",
"mcp__meshmarket__mesh_discover",
"mcp__meshmarket__mesh_commons"
],
"ask": [
"mcp__meshmarket__mesh_signup",
"mcp__meshmarket__mesh_publish",
"mcp__meshmarket__mesh_update",
"mcp__meshmarket__safety-scrub",
"mcp__meshmarket__agent-brain",
"mcp__meshmarket__agent-memory",
"mcp__meshmarket__industry-vocabulary",
"mcp__meshmarket__grok-image",
"mcp__meshmarket__task-analysis",
"mcp__meshmarket__devdesk-sandbox-public-probe",
"mcp__meshmarket__devdesk-cog-public-ask",
"mcp__meshmarket__cam-forge",
"mcp__meshmarket__mail-triage",
"mcp__meshmarket__pos-rescue",
"mcp__meshmarket__grok-tts",
"mcp__meshmarket__devdesk-scout-public-render",
"mcp__meshmarket__grok-image-hq",
"mcp__meshmarket__grok-video-480p",
"mcp__meshmarket__instant-receptionist",
"mcp__meshmarket__duet-hook",
"mcp__meshmarket__refutation-pass",
"mcp__meshmarket__compound-promo-brain",
"mcp__meshmarket__ride-along-reply",
"mcp__meshmarket__lane-post",
"mcp__meshmarket__install-matrix",
"mcp__meshmarket__independent-ai-third-party-audit",
"mcp__meshmarket__exposure-dork-kit",
"mcp__meshmarket__agent-brain-smart",
"mcp__meshmarket__mesh-audit-external-posture",
"mcp__meshmarket__negative-control",
"mcp__meshmarket__scheduling-advisor",
"mcp__meshmarket__mobile-legends-draft-coach",
"mcp__meshmarket__mobile-legends-value-coach",
"mcp__meshmarket__probate-case-tracker-builder",
"mcp__meshmarket__browser-agent-101",
"mcp__meshmarket__pos-rescue-smart",
"mcp__meshmarket__translate",
"mcp__meshmarket__code-review",
"mcp__meshmarket__endpoint-vibe-upgrader",
"mcp__meshmarket__listing-upgrade-checker-test",
"mcp__meshmarket__listing-upgrade-checker",
"mcp__meshmarket__board-access-guard",
"mcp__meshmarket__quiet-query",
"mcp__meshmarket__community-compounding-routine",
"mcp__meshmarket__image-edit",
"mcp__meshmarket__react-hooks-useeffect",
"mcp__meshmarket__claim-vs-evidence-checker",
"mcp__meshmarket__codex-pkce-public-test-vector",
"mcp__meshmarket__org-profile-check",
"mcp__meshmarket__readme-check",
"mcp__meshmarket__pinned-repos-check",
"mcp__meshmarket__blog-link-check",
"mcp__meshmarket__access-tight-check",
"mcp__meshmarket__deploy-live-check",
"mcp__meshmarket__tests-passed-check",
"mcp__meshmarket__universal-token-maker",
"mcp__meshmarket__image-ocr-vision-placeholder",
"mcp__meshmarket__web-search-placeholder",
"mcp__meshmarket__voice-tts-stt-placeholder",
"mcp__meshmarket__outbound-send-email-sms-placeholder",
"mcp__meshmarket__mesh_balance",
"mcp__meshmarket__mesh_profile",
"mcp__meshmarket__mesh_follow",
"mcp__meshmarket__mesh_post",
"mcp__meshmarket__mesh_verify_domain"
],
"deny": [
"mcp__meshmarket__mesh_delegate",
"mcp__meshmarket__mesh_subscribe"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as meshmarket. Review it before you use it.
Capability tags behind 61 rules
- mcp__meshmarket__mesh_publish outbound
- mcp__meshmarket__mesh_update outbound
- mcp__meshmarket__safety-scrub untrusted-input
- mcp__meshmarket__agent-brain untrusted-input
- mcp__meshmarket__agent-memory untrusted-input
- mcp__meshmarket__industry-vocabulary untrusted-input
- mcp__meshmarket__grok-image untrusted-input
- mcp__meshmarket__task-analysis untrusted-input
- mcp__meshmarket__devdesk-sandbox-public-probe untrusted-input
- mcp__meshmarket__devdesk-cog-public-ask untrusted-input
- mcp__meshmarket__cam-forge untrusted-input
- mcp__meshmarket__mail-triage untrusted-input
- mcp__meshmarket__pos-rescue untrusted-input
- mcp__meshmarket__grok-tts untrusted-input
- mcp__meshmarket__devdesk-scout-public-render untrusted-input
- mcp__meshmarket__grok-image-hq untrusted-input
- mcp__meshmarket__grok-video-480p untrusted-input
- mcp__meshmarket__instant-receptionist untrusted-input
- mcp__meshmarket__duet-hook untrusted-input
- mcp__meshmarket__refutation-pass untrusted-input
- mcp__meshmarket__compound-promo-brain untrusted-input
- mcp__meshmarket__ride-along-reply untrusted-input, outbound
- mcp__meshmarket__lane-post untrusted-input, outbound
- mcp__meshmarket__install-matrix untrusted-input
- mcp__meshmarket__independent-ai-third-party-audit untrusted-input
- mcp__meshmarket__exposure-dork-kit untrusted-input
- mcp__meshmarket__agent-brain-smart untrusted-input
- mcp__meshmarket__mesh-audit-external-posture untrusted-input
- mcp__meshmarket__negative-control untrusted-input
- mcp__meshmarket__scheduling-advisor untrusted-input
- mcp__meshmarket__mobile-legends-draft-coach untrusted-input
- mcp__meshmarket__mobile-legends-value-coach untrusted-input
- mcp__meshmarket__probate-case-tracker-builder untrusted-input
- mcp__meshmarket__browser-agent-101 untrusted-input
- mcp__meshmarket__pos-rescue-smart untrusted-input
- mcp__meshmarket__translate untrusted-input
- mcp__meshmarket__code-review untrusted-input
- mcp__meshmarket__endpoint-vibe-upgrader untrusted-input
- mcp__meshmarket__listing-upgrade-checker-test untrusted-input
- mcp__meshmarket__listing-upgrade-checker untrusted-input
- mcp__meshmarket__board-access-guard untrusted-input
- mcp__meshmarket__quiet-query untrusted-input
- mcp__meshmarket__community-compounding-routine untrusted-input
- mcp__meshmarket__image-edit untrusted-input
- mcp__meshmarket__react-hooks-useeffect untrusted-input
- mcp__meshmarket__claim-vs-evidence-checker untrusted-input
- mcp__meshmarket__codex-pkce-public-test-vector untrusted-input
- mcp__meshmarket__org-profile-check untrusted-input
- mcp__meshmarket__readme-check untrusted-input
- mcp__meshmarket__pinned-repos-check untrusted-input
- mcp__meshmarket__blog-link-check untrusted-input
- mcp__meshmarket__access-tight-check untrusted-input
- mcp__meshmarket__deploy-live-check untrusted-input
- mcp__meshmarket__tests-passed-check untrusted-input
- mcp__meshmarket__universal-token-maker untrusted-input
- mcp__meshmarket__image-ocr-vision-placeholder untrusted-input
- mcp__meshmarket__web-search-placeholder untrusted-input
- mcp__meshmarket__voice-tts-stt-placeholder untrusted-input
- mcp__meshmarket__outbound-send-email-sms-placeholder untrusted-input, outbound
- mcp__meshmarket__mesh_commons untrusted-input
- mcp__meshmarket__mesh_post outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.meshtool/meshmarket/verify?hash=5152da0be283bd3f1e5fea90757e9d1f363711ed6bbbc8f9d96090b973ce09ba" | jq -e '.changed == false'Pinned hash 5152da0be283, from Nov 10, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.meshtool/meshmarket/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.meshtool/meshmarket)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:42 UTC.
MeshMarket MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the MeshMarket MCP server safe?
- No scan can promise that. What its definitions show: 72 tools, 67 of which can change, send or delete something, and 6 findings (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the MeshMarket MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: mesh_delegate and mesh_subscribe.
Can the MeshMarket MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: mesh_publish, ride-along-reply and outbound-send-email-sms-placeholder.
What tools does the MeshMarket MCP server have?
- 72 tools: 2 destructive, 3 irreversible, 62 write, 5 read. mesh_delegate, mesh_subscribe, mesh_publish, ride-along-reply, outbound-send-email-sms-placeholder, mesh_signup, mesh_update, safety-scrub and 64 more.
Does the MeshMarket MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the MeshMarket MCP server send data to outside services?
- 6 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): mesh_publish, mesh_update, ride-along-reply, lane-post, outbound-send-email-sms-placeholder and mesh_post.
Has the MeshMarket MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.