Developer · Local MCP server

Project Brain

Read-only source search and retrieval across configured GitHub repositories.

What the MCP Registry states

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

Registry name
io.github.Gentleelephant/project-brain
Version
2.0.3
Status
Active
Category
developer
Transport
stdio (local process)
Package
OCI image (Docker)
Published
2026-08-08
Updated
2026-08-08
Publisher
Gentleelephant (GitHub)
Repository
github.com/Gentleelephant/project-brain
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
OCI image (Docker)ghcr.io/gentleelephant/project-brain:v2.0.3—stdioPROJECT_BRAIN_REPO_LIST (required), PROJECT_BRAIN_STATE_DIR (required), PB_GITHUB_TOKEN (secret), PB_FETCH_TTL

How to connect Project Brain

Project Brain runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/gentleelephant/project-brain:v2.0.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm -e PROJECT_BRAIN_REPO_LIST -e PROJECT_BRAIN_STATE_DIR -e PB_GITHUB_TOKEN -e PB_FETCH_TTL ghcr.io/gentleelephant/project-brain:v2.0.3. It reads these environment variables: PROJECT_BRAIN_REPO_LIST (required), PROJECT_BRAIN_STATE_DIR (required), PB_GITHUB_TOKEN (secret) and PB_FETCH_TTL; set them in the client's configuration for this server.

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

{
  "mcpServers": {
    "project-brain": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PROJECT_BRAIN_REPO_LIST",
        "-e",
        "PROJECT_BRAIN_STATE_DIR",
        "-e",
        "PB_GITHUB_TOKEN",
        "-e",
        "PB_FETCH_TTL",
        "ghcr.io/gentleelephant/project-brain:v2.0.3"
      ],
      "env": {
        "PROJECT_BRAIN_REPO_LIST": "<value>",
        "PROJECT_BRAIN_STATE_DIR": "<value>",
        "PB_GITHUB_TOKEN": "<secret>",
        "PB_FETCH_TTL": "<value>"
      }
    }
  }
}

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 6,250 →
ServerRunsEndpoint or package
ProfileProfile server for kazejev.com: biography, skills, projects and education.Remote · HTTPmcp.kazejev.com
ProfitCollector22 pay-per-call developer, security, network and data utilities using x402 on Base.Remote · HTTPmcp.bakhour.ca
ProfitPlayMCP server for the live ProfitPlay BTC five-minute AI agent sandbox.Local · stdioOCI image (Docker): ghcr.io/jarvismaximum-hue/profitplay-mcp:0.1.0
ProfusiaGive your AI a place to publish: living pages with live data, shareable links, no deploy pipeline.Remote · HTTPprofusia.ai
Project ContextSafely manage repository-scoped issues across Linear, GitHub Issues, and Jira Cloud.Local · stdionpm: @sandovalrr/project-context-mcp
Project Memory MCPPersistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.Local · stdionpm: @kaaustubh/project-memory-mcp
ProjectmemCoding agent memory — one local MCP server for every project. Warns before repeating failed fixes.Local · stdioPyPI: projectmem
projectmindPersistent project memory for AI coding agents: one compact digest instead of re-reading the repo.Local · stdionpm: @nodemint/projectmind