Skip to content

Agent Provenance MCP server

io.github.jdhart81/agent-provenancejdhart81streamable-httpv0.2.1Scanned

Birth certificates, lineage and cascading recalls for agents.

11 tools: 1 can delete or cancel things, 5 change things and 5 only read.

Tools: 1 delete, 0 irreversible, 5 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • 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 Provenance MCP server can do

The Agent Provenance MCP server is published by the GitHub account jdhart81. It has 11 tools. It can delete or cancel things (1 tool: recall) and create or change data (5 tools: register_genesis, verify_certificate, lineage, register_artifact and 1 more). 5 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 16, 2026, version 0.2.1.

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.

11 tools

Deletes or cancels 1Claude Code: deny
  • recallRecall an agent: flags it and quarantines every transitive descendant.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
    Recall an agent: flags it and quarantines every transitive descendant. Reports exactly which agents were quarantined.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
    • title: Recall
Changes things 5Claude Code: ask
  • lineageFull ancestry and descendants of an agent, plus its generation number.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
    Full ancestry and descendants of an agent, plus its generation number.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
    • title: Lineage
  • register_artifactRegister a content-addressed artifact in a separate provenance DAG.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
    Register a content-addressed artifact in a separate provenance DAG. Parent hashes may be registered artifacts or external content roots. Idempotent on artifact_id; does not consume a genesis index.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
    • title: Register artifact
  • register_genesisRegister an agent's birth.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
    Register an agent's birth. Issues a content-addressed genesis certificate with a strictly monotone index (epoch 0 = the founding cohort). parent_id records lineage; children of recalled/quarantined parents are quarantined at birth. Idempotent — an agent is born once.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • readOnlyHint: false
    • title: Register genesis
  • verify_artifactRecompute an artifact record hash and verify it against the DAG ledger.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
    Recompute an artifact record hash and verify it against the DAG ledger.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Verify artifact
  • verify_certificateVerify a certificate: recompute its content hash and check the ledger.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
    Verify a certificate: recompute its content hash and check the ledger.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Verify certificate
Only reads 5Show 5 read-only tools
  • describe_agentDescribe this agent: name, version, purpose, every action it supports and the inputs each one takes.No findings

    Why it is in this group

    • The name "describe_agent" says "describe": a word for reading.
    Description, as the server wrote it
    Describe this agent: name, version, purpose, every action it supports and the inputs each one takes. Read-only and free; call it first to learn how to use this server.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Describe this service
  • get_artifactFetch one registered artifact by artifact_id.No findings

    Why it is in this group

    • The name "get_artifact" says "get": a word for reading.
    Description, as the server wrote it
    Fetch one registered artifact by artifact_id.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Get artifact
  • get_certificateFetch an agent's genesis certificate + recall/quarantine status.No findings

    Why it is in this group

    • The name "get_certificate" says "get": a word for reading.
    Description, as the server wrote it
    Fetch an agent's genesis certificate + recall/quarantine status.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Get certificate
  • list_artifactsList artifacts, optionally filtered by producer agent.No findings

    Why it is in this group

    • The name "list_artifacts" says "list": a word for reading.
    Description, as the server wrote it
    List artifacts, optionally filtered by producer agent.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List artifacts
  • list_recordsList genesis records, optionally by epoch (0 = founding cohort).No findings

    Why it is in this group

    • The name "list_records" says "list": a word for reading.
    Description, as the server wrote it
    List genesis records, optionally by epoch (0 = founding cohort).

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List records

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 or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:27 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
6
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 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.viridisconservation.com/provenance/mcp: tools/list returned 11 tools to an anonymous client, including recall (destructive), register_genesis (write), verify_certificate (write), lineage (write), register_artifact (write) and 1 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. Tools10 changed.~10 changedView diff
  2. Tools11 changed.~11 changedView diff

Install

Pinned to version 0.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-provenance https://mcp.viridisconservation.com/provenance/mcp
claude mcp add --transport http agent-provenance https://mcp.viridisconservation.com/provenance/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-provenance__get_certificate",
      "mcp__agent-provenance__list_records",
      "mcp__agent-provenance__get_artifact",
      "mcp__agent-provenance__list_artifacts",
      "mcp__agent-provenance__describe_agent"
    ],
    "ask": [
      "mcp__agent-provenance__register_genesis",
      "mcp__agent-provenance__verify_certificate",
      "mcp__agent-provenance__lineage",
      "mcp__agent-provenance__register_artifact",
      "mcp__agent-provenance__verify_artifact"
    ],
    "deny": [
      "mcp__agent-provenance__recall"
    ]
  }
}

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-provenance. Review it before you use it.

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-provenance/verify?hash=15c6b1693043dac6025df159106df51c4bb0ffed6fc1977a2c9f43bfb7eee618" | jq -e '.changed == false'

Pinned hash 15c6b1693043, from Nov 16, 2026, 02:18 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-provenance/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Nov 16, 2026, 02:17 UTC.

Agent Provenance MCP server: questions and answers

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

Is the Agent Provenance MCP server safe?

No scan can promise that. What its definitions show: 11 tools, 6 of which can change, send or delete something, and 0 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 Provenance MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: recall.

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

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Agent Provenance MCP server have?

11 tools: 1 destructive, 5 write, 5 read. recall, register_genesis, verify_certificate, lineage, register_artifact, verify_artifact, get_certificate, list_records and 3 more.

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

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

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

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Agent Provenance MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.