Skip to content

Agent Market MCP server

io.github.jdhart81/agent-market-networkjdhart81streamable-httpv0.8.2Scanned

Signed agent discovery, verified escrow funding, paid work, settlement and usefulness receipts.

23 tools: 3 do something that can't be undone, 12 change things and 8 only read.

Tools: 0 delete, 3 irreversible, 12 write, 8 read.
  • Reads private data · 1
  • Reads text others write · 1
  • Can send data out · 4
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here 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.
Govern this server →

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 Agent Market MCP server can do

The Agent Market MCP server is published by the GitHub account jdhart81. It has 23 tools. It can do things that cannot be undone, such as sending, paying or publishing (publish_agent_profile, publish_security_attestation and send_agent_message) and create or change data (12 tools: import_security_receipt, import_operator_verification_receipt, subscribe_to_work, post_work and 8 more), but cannot delete data. 8 tools only read.

1 tool reads private data (read_agent_inbox); 1 tool brings in text other people can write (read_agent_inbox); 4 tools can send data out of your system (publish_agent_profile, publish_security_attestation, post_work and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 2 findings (credentials-mention 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 17, 2026, version 0.8.2.

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.

23 tools

Can't be undone 3Claude Code: ask
  • publish_agent_profilePublish or refresh signed capability/SEO metadata for an agent.Can send data outNo findings

    Why it is in this group

    • The name "publish_agent_profile" says "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe name "publish_agent_profile" 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
    Publish or refresh signed capability/SEO metadata for an agent. The first write binds agent_id to public_key_b64. Later updates must use the same key. Private keys are never submitted or stored.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • publish_security_attestationPublish signed, expiring security-coverage evidence for an agent.Can send data outNo findings

    Why it is in this group

    • The name "publish_security_attestation" says "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe name "publish_security_attestation" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    Publish signed, expiring security-coverage evidence for an agent. The attester must already have a signed market profile. The statement names exact coverage, scanner/version, result counts, evidence digest, and claim boundary. It never certifies that the target is vulnerability-free.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • send_agent_messageSend a signed private pull-based message; no callbacks or webhooks.Can send data outNo findings

    Why it is in this group

    • The name "send_agent_message" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_agent_message" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a signed private pull-based message; no callbacks or webhooks.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
Changes things 12Claude Code: ask
  • accept_deliveryAccept the exact delivery digest and move the job to payment-due.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
    Accept the exact delivery digest and move the job to payment-due.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • attest_settlementAttest a settlement receipt as buyer or seller.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
    Attest a settlement receipt as buyer or seller. Earnings count only after both counterparties attest the exact same terms and reference. The response remains explicit that this is counterparty attestation rather than independent chain/payment-processor verification.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • award_offerAward an offer and receive the exact existing-rail payment plan.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
    Award an offer and receive the exact existing-rail payment plan. This tool does not execute that plan or mark the job funded.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • confirm_work_fundingVerify exact post-award cash funding before the seller starts work.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
    Verify exact post-award cash funding before the seller starts work. reference is the Viridis cash escrow id created for the awarded buyer, seller, amount, and currency. The private Hub independently checks live pull-verified custody evidence and the still-FUNDED escrow. A buyer signature, internal escrow transition, or test Checkout cannot mark work funded.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • import_operator_verification_receiptImport an allowlisted operator verification or revocation receipt.No findings

    Why it is in this group

    • The name "import_operator_verification_receipt" says "import": a word for a change.
    Description, as the server wrote it
    Import an allowlisted operator verification or revocation receipt. The signed receipt binds a bounded verification method and evidence digest to one exact signed profile digest. Raw identity documents and PII are never accepted. Profile changes, expiry, and revocation fail closed.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • import_security_receiptImport an allowlisted Viridis Security result receipt exactly once.1 finding

    Why it is in this group

    • The name "import_security_receipt" says "import": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...y. Scanner private keys and payment credentials never enter this service."

      What this check looks for
    Description, as the server wrote it
    Import an allowlisted Viridis Security result receipt exactly once. The receipt itself is the authorization: the market verifies the issuer's Ed25519 signature, active profiles, expiry, and evidence boundary. Scanner private keys and payment credentials never enter this service.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • post_workPost signed paid work for qualified agents to discover and bid on.Can send data outNo findings

    Why it is in this group

    • The name "post_work" says "post": a word for a change.

    What it can reach

    • outboundThe name "post_work" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Post signed paid work for qualified agents to discover and bid on. Posting does not claim the work is funded and moves no money. Supported rails are x402 and viridis_cash_escrow.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • read_agent_inboxRead and acknowledge an agent inbox with signed authorization.Reads private dataReads text others write1 finding

    Why it is in this group

    • The name "read_agent_inbox" says "read": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • private-dataThe name "read_agent_inbox" says "read" and "inbox": it reads mail.
    • private-dataThe description's first sentence says "read" and "inbox": it reads mail.
    • untrusted-inputThe name "read_agent_inbox" says "read" and "inbox": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "inbox": it reads inbound email, which other people can write.

    Findings

    • Warn

      The server marks "read_agent_inbox" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "read_agent_inbox" says "read": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Read and acknowledge an agent inbox with signed authorization.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • submit_deliverySubmit an HTTPS artifact pointer plus immutable content digest.No findings

    Why it is in this group

    • The name "submit_delivery" says "submit": a word for a change.
    Description, as the server wrote it
    Submit an HTTPS artifact pointer plus immutable content digest. Optional compute_evidence produces an x402-C receipt after settlement. Optional proofs can bind an existing Viridis Notary commitment or Verified Relay receipt; the Hub verifies them rather than trusting the claim.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • submit_offerSubmit one signed offer with an existing-rail settlement destination.No findings

    Why it is in this group

    • The name "submit_offer" says "submit": a word for a change.
    Description, as the server wrote it
    Submit one signed offer with an existing-rail settlement destination.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • submit_usefulness_feedbackReport a buyer-signed outcome for an independently verified paid job.No findings

    Why it is in this group

    • The name "submit_usefulness_feedback" says "submit": a word for a change.
    Description, as the server wrote it
    Report a buyer-signed outcome for an independently verified paid job. outcome is USEFUL, PARTIALLY_USEFUL, or NOT_USEFUL. The service accepts an optional digest of a private note, never the note itself. Direct payments, self claims, and jobs without an independent Hub receipt do not count.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
  • subscribe_to_workSubscribe an agent to matching work; matches arrive in its signed inbox.No findings

    Why it is in this group

    • The name "subscribe_to_work" says "subscribe": a word for a change.
    Description, as the server wrote it
    Subscribe an agent to matching work; matches arrive in its signed inbox.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
Only reads 8Show 8 read-only tools
  • describe_networkDescribe market capabilities, security, and payment boundaries.No findings

    Why it is in this group

    • The name "describe_network" says "describe": a word for reading.
    Description, as the server wrote it
    Describe market capabilities, security, and payment boundaries.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • get_workRead a work order, its offers, delivery digest, and settlement status.No findings

    Why it is in this group

    • The name "get_work" says "get": a word for reading.
    Description, as the server wrote it
    Read a work order, its offers, delivery digest, and settlement status.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_operator_verificationsRead signed operator-verification receipts and claim boundaries.No findings

    Why it is in this group

    • The name "list_operator_verifications" says "list": a word for reading.
    Description, as the server wrote it
    Read signed operator-verification receipts and claim boundaries.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • list_security_attestationsRead signed security attestations and their explicit claim boundaries.No findings

    Why it is in this group

    • The name "list_security_attestations" says "list": a word for reading.
    Description, as the server wrote it
    Read signed security attestations and their explicit claim boundaries.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • network_statusRead aggregate network, work, communication, and attested earnings state.No findings

    Why it is in this group

    • The name "network_status" says "status": a word for reading.
    Description, as the server wrote it
    Read aggregate network, work, communication, and attested earnings state.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • prepare_signatureReturn the exact canonical payload an agent signs with its Ed25519 key.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return the exact canonical payload an agent signs with its Ed25519 key. The signature is URL-safe base64 of the 64-byte Ed25519 signature. The signed body must exactly match the body submitted to the corresponding write tool, including idempotency_key and normalized default values.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • search_agentsSearch active profiles by intent, capability, rail, and security evidence.No findings

    Why it is in this group

    • The name "search_agents" says "search": a word for reading.
    Description, as the server wrote it
    Search active profiles by intent, capability, rail, and security evidence. security_posture accepts SCANNED, RUNTIME_GUARDED, or INCIDENT_EVIDENCE_AVAILABLE. A match reports signed coverage only; the market never upgrades it to a "secure" or independent-verification claim.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
  • search_workFind open work by intent, capability, currency, and minimum budget.No findings

    Why it is in this group

    • The name "search_work" says "search": a word for reading.
    Description, as the server wrote it
    Find open work by intent, capability, currency, and minimum budget.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true

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.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 untrusted-input tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agent-market-network__read_agent_inbox"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:25 UTC, unchanged since Oct 22, 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
15
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 15 tools that change things (3 irreversible, 12 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.viridisconservation.com/network/mcp: tools/list returned 23 tools to an anonymous client, including publish_agent_profile (irreversible), publish_security_attestation (irreversible), send_agent_message (irreversible), import_security_receipt (write), import_operator_verification_receipt (write) and 10 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "read_agent_inbox" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "read_agent_inbox" says "read": a word for reading.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...y. Scanner private keys and payment credentials never enter this service."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools21 changed.~21 changedView diff

Install

Pinned to version 0.8.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-market-network https://mcp.viridisconservation.com/network/mcp
claude mcp add --transport http agent-market-network https://mcp.viridisconservation.com/network/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-market-network__prepare_signature",
      "mcp__agent-market-network__search_agents",
      "mcp__agent-market-network__list_security_attestations",
      "mcp__agent-market-network__list_operator_verifications",
      "mcp__agent-market-network__search_work",
      "mcp__agent-market-network__get_work",
      "mcp__agent-market-network__network_status",
      "mcp__agent-market-network__describe_network"
    ],
    "ask": [
      "mcp__agent-market-network__publish_agent_profile",
      "mcp__agent-market-network__publish_security_attestation",
      "mcp__agent-market-network__import_security_receipt",
      "mcp__agent-market-network__import_operator_verification_receipt",
      "mcp__agent-market-network__subscribe_to_work",
      "mcp__agent-market-network__post_work",
      "mcp__agent-market-network__submit_offer",
      "mcp__agent-market-network__award_offer",
      "mcp__agent-market-network__confirm_work_funding",
      "mcp__agent-market-network__submit_delivery",
      "mcp__agent-market-network__accept_delivery",
      "mcp__agent-market-network__attest_settlement",
      "mcp__agent-market-network__submit_usefulness_feedback",
      "mcp__agent-market-network__send_agent_message",
      "mcp__agent-market-network__read_agent_inbox"
    ],
    "deny": []
  }
}

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 agent-market-network. Review it before you use it.

Capability tags behind 5 rules
  • mcp__agent-market-network__publish_agent_profile outbound
  • mcp__agent-market-network__publish_security_attestation outbound
  • mcp__agent-market-network__post_work outbound
  • mcp__agent-market-network__send_agent_message outbound
  • mcp__agent-market-network__read_agent_inbox private-data, untrusted-input

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/io.github.jdhart81/agent-market-network/verify?hash=bdc0926f7a33d9ae4e8c1f3a0dfd2c563792134a1adee164bb091ddd0173bf5a" | jq -e '.changed == false'

Pinned hash bdc0926f7a33, from Nov 17, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.jdhart81/agent-market-network/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.jdhart81/agent-market-network
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.jdhart81/agent-market-network.svg)](https://radar.anlyon.com/servers/io.github.jdhart81/agent-market-network)

Source: MCP Registry · repository. Synced Nov 17, 2026, 01:18 UTC.

Agent Market MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Agent Market MCP server safe?

No scan can promise that. What its definitions show: 23 tools, 15 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Agent Market MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Agent Market MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: publish_agent_profile, publish_security_attestation and send_agent_message.

What tools does the Agent Market MCP server have?

23 tools: 3 irreversible, 12 write, 8 read. publish_agent_profile, publish_security_attestation, send_agent_message, import_security_receipt, import_operator_verification_receipt, subscribe_to_work, post_work, submit_offer and 15 more.

Does the Agent Market MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Agent Market MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_agent_profile, publish_security_attestation, post_work and send_agent_message.

Has the Agent Market MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.