Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Bourdon

NPM · @GETBOURDON/MCP-SERVER · 2 COMPONENTS · SCANNED SEP 20

Recognition-first cross-agent memory federation. One shared memory across all your agents.

0 this week 82 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 52 of 138 dependencies flagged as unhealthy (1 deprecated). View diagnostics → Partial
Provenance & Transparency58
  • Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
  • Cryptographically verified build provenance (signed, bound to bourdonai/bourdon-js). View diagnostics → Pass
  • License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license. See how to fix → Fail
  • Actively maintained (last published 2 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability73
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 952 tokens (~59/item across 16 items; 15 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Bourdon MCP server?

Bourdon runs locally as an npm package, launched with npx -y @getbourdon/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @getbourdon/mcp-server

# add to Claude Code
claude mcp add ai-bourdon-bourdon -- npx -y @getbourdon/mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-bourdon-bourdon": {
      "command": "npx",
      "args": [
        "-y",
        "@getbourdon/mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-bourdon-bourdon": {
      "command": "npx",
      "args": [
        "-y",
        "@getbourdon/mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ai-bourdon-bourdon -- npx -y @getbourdon/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-bourdon-bourdon": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@getbourdon/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-bourdon-bourdon --command npx --arg -y --arg @getbourdon/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  ai-bourdon-bourdon:
    command: "npx"
    args: ["-y", "@getbourdon/mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-bourdon-bourdon": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@getbourdon/mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ai-bourdon-bourdon -t stdio -c npx -a -y @getbourdon/mcp-server
// mcp.json
{
  "mcpServers": {
    "ai-bourdon-bourdon": {
      "command": "npx",
      "args": [
        "-y",
        "@getbourdon/mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 17 Sept 26 +1
    • Stability: 0.97 → unverified security
    • Tool safety: pass → unverified security
    • Stability: 0.97 → pass security
    • Tool coverage: 100 → unverified functional
    • Capabilities: pass → unverified functional
    • Schema quality: 100 → unverified functional
    • Package version: 0.5.0 → 0.6.0 functional
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 10 Sept 26 +1
    • Stability: 0.97 → pass security
  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@getbourdon/mcp-server@0.6.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo bourdonai/bourdon-js
Certificate issuer https://gitlab.com
Certificate SAN https://gitlab.com/bourdonai/bourdon-js//.gitlab-ci.yml@refs/tags/v0.18.0
Rekor log index 2499938137
Predicate type https://slsa.dev/provenance/v0.2
Subject digest sha512:0c27c3ec74303bf26f1ca36446bdcdcde8c9c49ba66edaa76128fa10fb0afffcac7801ae0f4ae00f7a0e54f318899fb9b8b8423798a87df6392047775

Background: How many MCP packages publish verified provenance →

Dependencies 138 packages
Packages resolved 138
Deprecated 1
Stale 51
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 15 exposed · ~938 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
commit_to_federation ~112

Write a contribution to the federation under agent_id.

NameTypeReqDescription
agent_idstringyes
agent_typestring|null
entities
expected_digeststring|null
instancestring|null
modestring
notes
role_narrativestring|null
session_idstring|null
sessions
transcript_refstring|null
workstreams

No output schema declared.

No examples provided.

compile_codex_turn ~59

Compile a turn-scoped Codex recognition brief.

NameTypeReqDescription
access_levelstring
cwdstring|null
max_charsinteger
max_itemsinteger
promptstringyes

No output schema declared.

No examples provided.

explain_memory_change ~84

Which write produced a given state of an agent's memory: hand it a manifest digest (or a version's digest8) and it returns the caller, session, transcript, and what changed. session_id and transcript_ref are caller-asserted and unverified; the recorded caller identity is not.

NameTypeReqDescription
agent_idstringyes
digeststringyes

No output schema declared.

No examples provided.

export_agents ~23

Export THIS server's LOCAL agents only, source-attributed for the tray.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

find_entity ~49

Find an entity by name across all agents.

NameTypeReqDescription
access_levelstring
federation_hopinteger
include_privateboolean
namestringyes

No output schema declared.

No examples provided.

get_cross_agent_summary ~51

Aggregate everything the federation knows about a project.

NameTypeReqDescription
access_levelstring
federation_hopinteger
include_privateboolean
projectstringyes

No output schema declared.

No examples provided.

get_deeper_context ~44

Return post-recognition L2 context for the prompt.

NameTypeReqDescription
access_levelstring
include_privateboolean
promptstringyes

No output schema declared.

No examples provided.

list_agents ~33

List agent IDs known to this L6 server, plus any peers' agents.

NameTypeReqDescription
federation_hopinteger

No output schema declared.

No examples provided.

list_memory_versions ~62

Prior states of one agent's memory, newest first. Each row carries an opaque version_id to pass to rollback_agent_memory and a digest8 that joins to the provenance entry explaining which session produced it.

NameTypeReqDescription
agent_idstringyes
limit

No output schema declared.

No examples provided.

list_notes ~63

Return a page of freestanding notes across agents.

NameTypeReqDescription
access_levelstring
agentstring|null
cursorstring|null
include_privateboolean
limit
sincestring|null

No output schema declared.

No examples provided.

list_recent_work ~83

Return a page of sessions across agents (or a single agent).

NameTypeReqDescription
access_levelstring
agentstring|null
cursorstring|null
federation_hopinteger
include_privateboolean
limit
sincestring|null
summaryboolean

No output schema declared.

No examples provided.

list_workstreams ~50

List ongoing multi-session workstreams across agents.

NameTypeReqDescription
access_levelstring
agentstring|null
include_privateboolean
statusstring|null

No output schema declared.

No examples provided.

prepare_recognition_context ~52

Return immediate recognition and a bounded prompt-context fragment.

NameTypeReqDescription
access_levelstring
federation_hopinteger
include_privateboolean
promptstringyes

No output schema declared.

No examples provided.

query_agent_memory ~52

Find entries in one agent's L5 that match a topic.

NameTypeReqDescription
access_levelstring
agentstringyes
include_privateboolean
topicstringyes

No output schema declared.

No examples provided.

rollback_agent_memory ~121

Restore an archived version of an agent's memory. TRUSTED ONLY — the most destructive operation the server exposes: it discards every contribution made after the chosen version, including other agents'. Pass expected_digest when the decision took a while, so a commit that landed meanwhile fails the restore instead of being silently erased. The restore is itself snapshotted first, so a rollback is undoable.

NameTypeReqDescription
agent_idstringyes
expected_digeststring|null
session_idstring|null
version_idstringyes

No output schema declared.

No examples provided.

Common questions

What is the Bourdon MCP server?

Bourdon is an MCP server listed in the public MCP registry as ai.bourdon/bourdon. Recognition-first cross-agent memory federation. One shared memory across all your agents. This page covers its npm package (@getbourdon/mcp-server).

Is the Bourdon MCP server safe to use?

Bourdon scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Bourdon MCP server expose?

Bourdon exposes 15 tools: query_agent_memory, list_recent_work, list_workstreams, list_notes, find_entity, and 10 more. Their descriptions and schemas cost roughly 938 tokens of context every time the server is loaded.

Is the Bourdon MCP server still maintained?

Bourdon is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Bourdon MCP server under?

Bourdon declares the BUSL-1.1 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.