Developer · Local MCP server

Bourdon

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

Visit Bourdon's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
ai.bourdon/bourdon
Version
0.28.2
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI, npm
Published
2026-10-01
Updated
2026-10-01
Publisher
ai.bourdon
Namespace
Namespace verified by the MCP Registry via the domain bourdon.ai · how
Website
bourdon.ai
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIbourdon0.28.2stdioNone declared
npm@getbourdon/mcp-server0.11.0stdioNone declared

How to connect Bourdon

Bourdon runs locally from a Python package published to PyPI: bourdon version 0.28.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx bourdon.

Bourdon runs locally from a Node.js package published to the npm registry: @getbourdon/mcp-server version 0.11.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y @getbourdon/mcp-server@0.11.0.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "bourdon": {
      "command": "uvx",
      "args": [
        "bourdon"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
BoundaryaiDeterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.Remote · HTTPLive check: sign-in requiredmcp.boundaryai.ai
bounty-mcpLive coding-bounty deal-flow from verified-escrow GitHub bounties for AI agents.Local · stdionpm: @weiseer/bounty-mcp
BountyVerdict Agent Decision ToolsRead-only GitHub bounty, agent harness, Actions failure, flake, and MCP tool-drift decisions.Remote · HTTPLive check: ✗ no handshakebountyverdict-agent-production.mimirslab.workers.dev
BountyVerdict Agent Decision ToolsFree selector plus read-only GitHub bounty, agent harness, Actions, flake, and MCP drift decisions.Remote · HTTPLive check: ✗ no handshakebountyverdict-agent-production.mimirslab.workers.dev
BovediaMemoria personal para Claude Code en notas Markdown; no carga el contexto a ciegas.Local · stdionpm: bovedia
BoyceDeterministic SQL compiler for AI agents. Your agent stops guessing SQL.Local · stdioPyPI: boyce
Br8nCapture dev context on interrupt; replay it as a 30-second resume card. Git stash for your head.Local · stdioPyPI: br8n
brain - the recorderRecords your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.Local · stdioPyPI: brain-mcp