What are the prerequisites to run Github Second Brain?
You need Docker installed and running, and a GitHub Personal Access Token with appropriate permissions for the GitHub APIs the server will use.
@BaoNguyen09
Basic information
Providing tools to AI to explore github codebase like agent
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"github-second-brain": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GITHUB_PERSONAL_ACCESS_TOKEN",
"ghcr.io/baonguyen09/github-second-brain:latest"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_PERSONAL_GITHUB_ACCESS_TOKEN"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Github Second Brain is a self-hosted MCP (Model Context Protocol) server that gives AI assistants a set of tools to explore and understand GitHub repositories on demand. It connects an AI client to GitHub repos so the AI can fetch issues, file content, directory trees, and code diffs, enabling more accurate, grounded responses without hallucinations. It is open-source, free, and does not collect personal data or store queries.
Install by running a Docker container with a GitHub Personal Access Token. Configure the server in Claude Desktop or Cursor by adding a JSON entry to the MCP configuration, specifying the Docker command and token. Once running, prompt your AI assistant with code or documentation questions; the AI uses the server’s tools (with your approval) to retrieve repository data.
You need Docker installed and running, and a GitHub Personal Access Token with appropriate permissions for the GitHub APIs the server will use.
Your AI assistant connects to a local MCP server built from a Docker image. When you ask a repo-related question, the AI sends requests to use the server’s tools, which execute API calls and return relevant data, allowing the AI to generate a grounded response.
It provides `get_tree_directory` (full tree directory), `get_repo_contents` (file/folder content), `get_issue_context` (issue details and comments), and `get_code_diff` (diff for pull requests, branches, tags, commits). The `get_processed_repo` tool is deprecated.
Yes. It is open-source, completely free to use, and self-hosted. It does not collect personal information or store queries, so all data stays on your machine.
It is licensed under the Apache License 2.0.
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed).
Yuque mcp server

Model Context Protocol Servers

Model Context Protocol Servers
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from https://github.com/nguyenvanduocit/all-in-one-model-context-protocol
Comments