GitHub Brain

v1.0.0Version Controlstable

An experimental GitHub MCP server with local database.

githubgolanggraphqlmcpmcp-server
Share:
76
Stars
0
Downloads
0
Weekly
0/5

What is GitHub Brain?

GitHub Brain is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to experimental github mcp server with local database.

An experimental GitHub MCP server with local database.

This server falls under the Version Control category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An experimental GitHub MCP server with local database.

Use Cases

GitHub data with local caching
GraphQL-based repository analysis
Experimental GitHub integration
wham

Maintainer

LicenseMIT
Languagego
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx github-brain

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use GitHub Brain

GitHub Brain is an MCP server that caches GitHub organization data — issues, pull requests, and discussions — into a local SQLite database and then exposes that data to AI assistants for fast, token-efficient querying. Unlike calling the GitHub API directly, GitHub Brain pre-fetches and indexes data locally so that AI queries against thousands of issues or PRs are quick and avoid rate-limit problems. It is built with Go and uses GraphQL to pull data from GitHub, making it well-suited for engineering teams that want AI-assisted analysis of their organization's activity without exhausting API quotas.

Prerequisites

  • Node.js installed (for npx) or the github-brain binary installed globally
  • A GitHub Personal Access Token or OAuth token with read access to the target organization
  • The target GitHub organization name
  • An MCP-compatible client such as Claude Desktop or VS Code
1

Install github-brain

Install github-brain globally via npm, or use npx to run it without a global install.

npm install -g github-brain
# or use without installing:
npx github-brain@latest
2

Run the interactive TUI to configure and pull data

Before using it as an MCP server, run github-brain in interactive mode to authenticate and populate the local SQLite database with your organization's GitHub data.

github-brain
3

Set up authentication credentials

Create the configuration file at ~/.github-brain/.env with your GitHub token and organization name. You can also set these during the interactive TUI setup.

# ~/.github-brain/.env
GITHUB_TOKEN=your_github_token
ORGANIZATION=my-org
4

Configure your MCP client to use github-brain as an MCP server

Add github-brain to your MCP client config. The -o flag specifies the organization, which is required for MCP server mode.

{
  "mcpServers": {
    "github-brain": {
      "command": "npx",
      "args": ["github-brain@latest", "-o", "my-org"]
    }
  }
}
5

Restart your MCP client and verify

Restart Claude Desktop or your MCP client. Ask the AI to query issues or pull requests from your organization to confirm the server is working and the local database is populated.

GitHub Brain Examples

Client configuration

claude_desktop_config.json entry for GitHub Brain MCP server targeting a specific GitHub organization.

{
  "mcpServers": {
    "github-brain": {
      "command": "npx",
      "args": ["github-brain@latest", "-o", "my-org"]
    }
  }
}

Prompts to try

Example prompts for querying cached GitHub data through the MCP server.

- "Summarize all open pull requests in the my-org organization from the last 30 days."
- "Which contributors submitted the most issues last month?"
- "List all discussions tagged with 'bug' from the past quarter."
- "Show me all PRs that were merged last week along with their reviewers."
- "Analyze issue activity trends for my-org over the past 3 months."

Troubleshooting GitHub Brain

No data returned — local database appears empty

Run github-brain in interactive TUI mode first (without the -o MCP flag) to authenticate and pull organization data. The MCP server queries the local SQLite database, so it must be populated before the server can answer queries.

GitHub API rate limit errors during data pull

Ensure GITHUB_TOKEN is set to a Personal Access Token with sufficient scopes (read:org, repo). If you hit rate limits, re-run the pull at off-peak hours or use a token with higher rate limits.

MCP server starts but the AI receives empty results

Verify the organization name passed with -o matches exactly the GitHub organization slug (case-sensitive). Check ~/.github-brain/.env to confirm ORGANIZATION is set correctly and the token has access to that org.

Frequently Asked Questions about GitHub Brain

What is GitHub Brain?

GitHub Brain is a Model Context Protocol (MCP) server that experimental github mcp server with local database. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install GitHub Brain?

Follow the installation instructions on the GitHub Brain GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with GitHub Brain?

GitHub Brain works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is GitHub Brain free to use?

Yes, GitHub Brain is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Version Control MCP Servers

Explore all version control servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "github-brain": { "command": "npx", "args": ["-y", "github-brain"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use GitHub Brain?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides