Tetrees MCP server
ai.tetrees.ex/mcpex.tetrees.aistreamable-httpv2.3.0Scanned
Own, grow and trade portable agent intelligence via TAIP/1 Packs and MCP.
26 tools: 1 do something that can't be undone, 16 change things and 9 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 1
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 Tetrees MCP server can do
The Tetrees MCP server is published by ex.tetrees.ai, a domain the MCP Registry verified. It has 26 tools. It can do things that cannot be undone, such as sending, paying or publishing (publish_ai_pack) and create or change data (16 tools: accept_ai_pack_terms, acquire_free_ai_pack, download_ai_pack, quote_agent_run and 12 more), but cannot delete data. 9 tools only read.
3 tools bring in text other people can write (download_ai_pack, run_ai_pack and execute_client_extension); 1 tool can send data out of your system (publish_ai_pack).
The fixed checks matched 4 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 2.3.0.
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.
26 tools
Can't be undone 1Claude Code: ask
publish_ai_packPublish the exact current version after every mandatory Agent AVCP gate passes.Can send data outNo findings
Why it is in this group
- The name "publish_ai_pack" says "publish": a word for a change that another call does not undo.
What it can reach
- outboundThe name "publish_ai_pack" says "publish": it sends or publishes something to other people.
Description, as the server wrote it Publish the exact current version after every mandatory Agent AVCP gate passes. Paid packs additionally need Stripe Connect before checkout.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Changes things 16Claude Code: ask
accept_ai_pack_growthNormalize a proposed delta with Tetrees Agent or provider-free portable normalization, run the deterministic growth gate, and append it to this owner only.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 Normalize a proposed delta with Tetrees Agent or provider-free portable normalization, run the deterministic growth gate, and append it to this owner only.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
accept_ai_pack_termsRecord the current account agreement required before creating, uploading, auditioning, or publishing a pack.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 Record the current account agreement required before creating, uploading, auditioning, or publishing a pack.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
acquire_free_ai_packCreate a revocable entitlement for a published free pack without Stripe.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create a revocable entitlement for a published free pack without Stripe.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
create_ai_pack_draftCreate an owner-bound AI Pack listing with the complete buyer guide and two concrete example uses.No findings
Why it is in this group
- The name "create_ai_pack_draft" says "create": a word for a change.
Description, as the server wrote it Create an owner-bound AI Pack listing with the complete buyer guide and two concrete example uses. Accept current terms first. Free drafts do not require Stripe Connect.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
download_ai_packReturn a short-lived entitlement-gated URL for the signed .taip envelope.Reads text others write1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "download_ai_pack" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The description's first verb is "return": a word for reading.
Description, as the server wrote it Return a short-lived entitlement-gated URL for the signed .taip envelope.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
execute_client_extensionExecute one method from an owned Pack through a user-configured HTTPS API, nested MCP server, or isolated local-skill child process.Reads text others write1 finding
Why it is in this group
- The name "execute_client_extension" says "execute": 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.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...-skill child process. Configuration and credentials stay in the local MCP process. Write me..."
Description, as the server wrote it Execute one method from an owned Pack through a user-configured HTTPS API, nested MCP server, or isolated local-skill child process. Configuration and credentials stay in the local MCP process. Write methods require an exact one-call confirmation.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
prepare_local_ai_pack_runReturn a host-readable execution plan for connecting this Pack to explicitly selected, Agent-AVCP-auditioned local skills, MCP tools, resources, prompts, or HTTPS APIs.1 finding
Why it is in this group
- The name "prepare_local_ai_pack_run" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "prepare_local_ai_pack_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "prepare_local_ai_pack_run" says "run": a word for a change.
Description, as the server wrote it Return a host-readable execution plan for connecting this Pack to explicitly selected, Agent-AVCP-auditioned local skills, MCP tools, resources, prompts, or HTTPS APIs. Tetrees does not execute client extensions on its hosted servers.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
propose_ai_pack_growthSelect a proposal from a successful run.No findings
Why it is in this group
- The description's first verb is "select": a word for a change.
Description, as the server wrote it Select a proposal from a successful run. This creates a reviewable delta and does not mutate the pack.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
quote_agent_runGet the exact worst-case Point reservation before using platform-funded inference.1 finding
Why it is in this group
- The name "quote_agent_run" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "quote_agent_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "quote_agent_run" says "run": a word for a change.
Description, as the server wrote it Get the exact worst-case Point reservation before using platform-funded inference. BYOK quotes zero model points.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
run_ai_packRun a Tetrees AI Pack.Reads text others writeNo findings
Why it is in this group
- The name "run_ai_pack" says "run": 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 Run a Tetrees AI Pack. Before acquisition, Points fund a stateless base preview. Ownership unlocks BYOK, saved growth and download; local files remain request-scoped.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
run_ai_pack_auditionRun version-bound integrity, model, regression, memory-isolation, injection, growth, and cost gates after explicit Point confirmation.No findings
Why it is in this group
- The name "run_ai_pack_audition" says "run": a word for a change.
Description, as the server wrote it Run version-bound integrity, model, regression, memory-isolation, injection, growth, and cost gates after explicit Point confirmation.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
select_ai_pack_growth_versionSet this account's default hosted intelligence checkpoint for an owned Pack.No findings
Why it is in this group
- The name "select_ai_pack_growth_version" says "select": a word for a change.
Description, as the server wrote it Set this account's default hosted intelligence checkpoint for an owned Pack. Use sequence 0 to return to the signed base Pack; selection never rewrites the seller Pack.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
submit_ai_pack_for_auditionMove a complete owner-bound draft into the immutable Agent AVCP queue after readiness passes.No findings
Why it is in this group
- The name "submit_ai_pack_for_audition" says "submit": a word for a change.
Description, as the server wrote it Move a complete owner-bound draft into the immutable Agent AVCP queue after readiness passes.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
update_ai_pack_draftUpdate seller-owned public metadata; immutable pack versions are never overwritten.No findings
Why it is in this group
- The name "update_ai_pack_draft" says "update": a word for a change.
Description, as the server wrote it Update seller-owned public metadata; immutable pack versions are never overwritten.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
upload_ai_packRead an explicit local .taip path, transfer it through the product-scoped private upload contract, and commit one immutable higher version.No findings
Why it is in this group
- The name "upload_ai_pack" says "upload": a word for a change.
Description, as the server wrote it Read an explicit local .taip path, transfer it through the product-scoped private upload contract, and commit one immutable higher version.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
upload_ai_pack_imageUpload one explicit local JPEG, PNG, WebP, or AVIF image to the seller-owned pack listing.No findings
Why it is in this group
- The name "upload_ai_pack_image" says "upload": a word for a change.
Description, as the server wrote it Upload one explicit local JPEG, PNG, WebP, or AVIF image to the seller-owned pack listing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Only reads 9Show 9 read-only tools
get_ai_pack_private_reportRead actionable owner-only failures and next actions without exposing them to buyers.No findings
Why it is in this group
- The name "get_ai_pack_private_report" says "get": a word for reading.
Description, as the server wrote it Read actionable owner-only failures and next actions without exposing them to buyers.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_ai_pack_reportRead the buyer-safe, version-bound Agent AVCP gates and scores for a published pack.No findings
Why it is in this group
- The name "get_ai_pack_report" says "get": a word for reading.
Description, as the server wrote it Read the buyer-safe, version-bound Agent AVCP gates and scores for a published pack.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_ai_pack_runtime_profileReturn the Pack-declared hosted skills, ephemeral attachment policy, and user-controlled MCP/API extensions before a run.No findings
Why it is in this group
- The name "get_ai_pack_runtime_profile" says "get": a word for reading.
Description, as the server wrote it Return the Pack-declared hosted skills, ephemeral attachment policy, and user-controlled MCP/API extensions before a run.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_ai_pack_submission_readinessReturn missing TAIP, metadata, and imagery requirements with exact next actions.No findings
Why it is in this group
- The name "get_ai_pack_submission_readiness" says "get": a word for reading.
Description, as the server wrote it Return missing TAIP, metadata, and imagery requirements with exact next actions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_agent_modelsList OpenAI, Claude, and Z.AI models, current server pricing, capabilities, BYOK support, and sample Point quotes.No findings
Why it is in this group
- The name "list_agent_models" says "list": a word for reading.
Description, as the server wrote it List OpenAI, Claude, and Z.AI models, current server pricing, capabilities, BYOK support, and sample Point quotes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_ai_pack_growthList growth checkpoints, the active checkpoint, hosted slot/byte usage and limits without exposing private memory contents.No findings
Why it is in this group
- The name "list_ai_pack_growth" says "list": a word for reading.
Description, as the server wrote it List growth checkpoints, the active checkpoint, hosted slot/byte usage and limits without exposing private memory contents.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_owned_ai_packsList purchased, claimed-free, and seller-owned packs available to this account.No findings
Why it is in this group
- The name "list_owned_ai_packs" says "list": a word for reading.
Description, as the server wrote it List purchased, claimed-free, and seller-owned packs available to this account.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
quote_ai_pack_auditionReturn exact version-bound Point quotes and Agent AVCP deliverables.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 exact version-bound Point quotes and Agent AVCP deliverables.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
search_ai_packsSearch the published agent-asset exchange by task or capability.No findings
Why it is in this group
- The name "search_ai_packs" says "search": a word for reading.
Description, as the server wrote it Search the published agent-asset exchange by task or capability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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 write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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, 18:28 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
- 17
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://ex.tetrees.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://ex.tetrees.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 17 tools that change things (1 irreversible, 16 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://ex.tetrees.ai/mcp: tools/list returned 26 tools to an anonymous client, including publish_ai_pack (irreversible), accept_ai_pack_terms (write), acquire_free_ai_pack (write), download_ai_pack (write), quote_agent_run (write) and 12 more
Findings
Matches of fixed checks, with the text they matched.
- Warndownload_ai_pack
The server marks "download_ai_pack" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The description's first verb is "return": a word for reading.
- Warnquote_agent_run
The server marks "quote_agent_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "quote_agent_run" says "run": a word for a change.
The server marks "prepare_local_ai_pack_run" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "prepare_local_ai_pack_run" says "run": a word for a change.
The description mentions "credentials".
What this check looks forMatched text
description: "...-skill child process. Configuration and credentials stay in the local MCP process. Write me..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http ex https://ex.tetrees.ai/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http ex https://ex.tetrees.ai/mcp --header 'Authorization: <your-authorization>'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.
{
"permissions": {
"allow": [
"mcp__ex__search_ai_packs",
"mcp__ex__list_owned_ai_packs",
"mcp__ex__get_ai_pack_report",
"mcp__ex__list_agent_models",
"mcp__ex__get_ai_pack_runtime_profile",
"mcp__ex__list_ai_pack_growth",
"mcp__ex__get_ai_pack_submission_readiness",
"mcp__ex__quote_ai_pack_audition",
"mcp__ex__get_ai_pack_private_report"
],
"ask": [
"mcp__ex__accept_ai_pack_terms",
"mcp__ex__acquire_free_ai_pack",
"mcp__ex__download_ai_pack",
"mcp__ex__quote_agent_run",
"mcp__ex__run_ai_pack",
"mcp__ex__prepare_local_ai_pack_run",
"mcp__ex__execute_client_extension",
"mcp__ex__propose_ai_pack_growth",
"mcp__ex__accept_ai_pack_growth",
"mcp__ex__select_ai_pack_growth_version",
"mcp__ex__create_ai_pack_draft",
"mcp__ex__update_ai_pack_draft",
"mcp__ex__upload_ai_pack",
"mcp__ex__upload_ai_pack_image",
"mcp__ex__submit_ai_pack_for_audition",
"mcp__ex__run_ai_pack_audition",
"mcp__ex__publish_ai_pack"
],
"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 ex. Review it before you use it.
Capability tags behind 4 rules
- mcp__ex__download_ai_pack untrusted-input
- mcp__ex__run_ai_pack untrusted-input
- mcp__ex__execute_client_extension untrusted-input
- mcp__ex__publish_ai_pack 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.tetrees.ex/mcp/verify?hash=24ba4a97a8f52556d9fed2b9338db58b710b233400e72fef89bbfe1d8f8a653d" | jq -e '.changed == false'Pinned hash 24ba4a97a8f5, from Nov 10, 2026, 04:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.tetrees.ex/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.tetrees.ex/mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:43 UTC.
Tetrees MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Tetrees MCP server safe?
- No scan can promise that. What its definitions show: 26 tools, 17 of which can change, send or delete something, and 4 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 Tetrees MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Tetrees MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: publish_ai_pack.
What tools does the Tetrees MCP server have?
- 26 tools: 1 irreversible, 16 write, 9 read. publish_ai_pack, accept_ai_pack_terms, acquire_free_ai_pack, download_ai_pack, quote_agent_run, run_ai_pack, prepare_local_ai_pack_run, execute_client_extension and 18 more.
Does the Tetrees MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Tetrees MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_ai_pack.
Has the Tetrees MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.