MCP GitHub Agent
Provides GitHub-shaped tools for AI agents, including listing issues, retrieving pull requests, and summarizing activity in a repository. Intended as a local agent demo; actions that would modify a repository (such as merging via apply) are refused.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP GitHub Agent
Overview
A tool-using agent that exposes GitHub-shaped tools in the style of the Model Context Protocol. GET /tools lists list_issues, get_pr and summarize, and POST /call invokes one of them. Merging a pull request through an apply action is refused, so the agent can read and summarize but not change a repository. A versioned /v1 ops API adds workspaces, tenant isolation, job approval and audit records.
Built with: Python, pytest, GitHub Actions
Scope: Local laptop lab with tests; it does not call a hosted model and refuses merges and production apply.
Related MCP server: github-pr-review
Project guide
Project architecture · Interview questions and answers
Use the architecture document for the component diagram, implementation boundaries, and verification entry points. The interview guide includes source-backed answers and project walkthroughs.
Implementation map
Component | Responsibility |
HTTP handlers: | |
Functions: | |
Implementation or supporting configuration | |
Implementation or supporting configuration | |
Executable checks and regression examples | |
GitHub Actions job definitions | |
Project explanations or operating notes |
Local setup and verification
From the repository root (the commands follow the checked-in manifests):
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
python -m pytest -qTo serve the FastAPI application locally, install the server separately if it is not already available:
python -m pip install uvicorn
PYTHONPATH=src python -m uvicorn mcpgh.main:app --reloadLevel: 10 — MCP & Tool-Using Agents
Skills: Python, GitHub-shaped tools
Tools: list_issues, get_pr, summarize. Merge via apply is refused.
pip install -r requirements.txt
pytest -qThis is a local laptop proof. It does not call a hosted model and it does not apply production changes.
Ops plane
Workspaces, tenant isolation, job approval, and audit live under /v1. Production apply is refused. See docs/ARCHITECTURE.md.
Documentation checks
Project architecture, interview guides, and local source links are checked automatically on pushes and pull requests. Run the same check locally:
python3 .github/scripts/validate_project_docs.pyTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.
Read and write KukGit repositories, files, issues and pull requests from an AI assistant.
Access the GitHub API, enabling file operations, repository management, search functionality, and…
Check GitHub pull requests and schedule, move, cancel or revert merges from an AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables LLM agents to search, read, and create GitHub issues and pull requests via natural language, using the GitHub API.1MIT
- FlicenseAqualityDmaintenanceEnables LLM clients to list, read, review, and comment on GitHub pull requests, turning an AI assistant into a fully capable code reviewer.61-
- AlicenseNot gradedqualityCmaintenanceA Model Context Protocol server that exposes read-only GitHub tools to LLM clients, enabling browsing of open issues, pull requests, issue details, and recent repository activity via natural language.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to answer natural-language GitHub queries by listing repositories, issues, pull requests, branches, commits, and files, as well as performing writes with dry-run and confirmation safeguards.-