
GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
- Remote
- Open source
- 34.6K GitHub stars
- Developer tools

Official MCP server connecting AI assistants to GitHub repos, issues and workflows

Run many coding agents in parallel, each on its own branch, with PR and CI feedback loops

Open-source CI runners and microVM sandboxes billed by runtime

Read-only SQL over your traces, logs, metrics and GitHub Actions CI runs
Not checked yet
Rank security scanner findings by exposure, criticality and exploitability
Runs locallyUpload screenshots and files from coding agents and attach them to GitHub PRs
Checks an agent's PR handback claims against GitHub's own record with no model involved
Runs locallyDeterministic checks that catch invented functions and untraceable claims in specs
Runs locallyOffline trust certificates for code repositories that anyone can re-run and verify
Runs locally
Finds why Playwright tests fail, proposes fixes and verifies them before keeping the edit
Runs locallyCheck a text file of links for status codes, broken pages and redirect chains
Runs locally
Test BGP and routing changes in a real containerlab lab before merge, with evidence
Runs locallyRun Slack, Gmail, Drive, GitHub and Jira APIs locally over one test corpus
Runs locallyTest RL environment graders for wrong answers they pay and right ones they reject
Runs locallyLint MCP tool schemas across eight clients and score how well agents recover from errors
Runs locallyRead-only preflight checks for MCP and x402 endpoints before an agent depends on them
Runs locallyOffline linter for questions sent to Jev and Luna decision models, callable by agents
Runs locallyPredicts the DDL a dbt change will run before you run it, from compiled SQL files
Runs locallyRecord AI agent verdicts bound to file hashes and refuse stale ones before shipping
Runs locallyOpen a React Native app in a simulated phone: read the screen, tap, type, set device state
Not checked yet
Fault-injection MCP server for testing how MCP clients handle timeouts and bad replies
Runs locallyStructural change control and code-health analysis for AI-assisted Python development
Runs locallyFail-closed merge gate that tells an AI coding agent MERGE, BLOCK or INCONCLUSIVE
Runs locallyRead-only MCP server that lets coding agents query Playwright test stability and failures
Runs locallyWork with repos, pull requests, CI runs and issues on a Diffinery git forge
Not checked yetCompare two Electron builds and see what changed in IPC, preload bridges and windows
Runs locallyHosted MCP server giving AI assistants access to Dodil data, git, app hosting and sign-in
Not checked yetCheck whether Chinese, Japanese and Korean page titles fit Google by pixel width
Runs locallyRun rooted Android emulators on Apple Silicon Macs, driven by a CLI or AI agents
Runs locallyRead Woodpecker CI pipelines and logs and run builds, secrets and crons from an agent
Runs locally