GitHub MCP Server

Created By
marvelouscyphermana year ago
MCP server for using the GitHub API
Overview

what is GitHub MCP Server?

GitHub MCP Server is a Model Context Protocol (MCP) server implementation designed for seamless integration with the GitHub API, allowing AI models to interact with GitHub repositories, issues, pull requests, and more.

how to use GitHub MCP Server?

To use the GitHub MCP Server, clone the repository, install the dependencies, configure your GitHub Personal Access Token, build the server, and start it. The server will run on port 3000 by default.

key features of GitHub MCP Server?

  • Full GitHub API integration
  • Support for repository operations (create, fork, search)
  • File operations (create, update, read)
  • Issue and PR management
  • Code search capabilities
  • Branch management
  • Commit history access

use cases of GitHub MCP Server?

  1. Automating repository management tasks.
  2. Integrating AI models for enhanced GitHub interactions.
  3. Real-time updates for GitHub events through Server-Sent Events.

FAQ from GitHub MCP Server?

  • How do I configure my GitHub token?

You can configure your GitHub token either through a configuration file or as an environment variable.

  • What is the default port for the server?

The server runs on port 3000 by default, but you can change it by setting the PORT environment variable.

  • Is there an example client for real-time updates?

Yes, a complete example client implementation can be found in examples/sse-client.html.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
marvelouscypherman
Star
0
Language
TypeScript
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago