Best for
- Development teams that need AI assistants to operate GitHub
- Users who want to handle repository collaboration tasks through natural language
- Deployers able to manage GitHub access tokens securely
G
GitHub
Official
Connect AI assistants to GitHub through natural language.
- Category
- Dev Tools #348 of 438
- Stars
- ★ 5.8k Very popular
- Transport
- stdio (local process) · Streamable HTTP
- Runtime
- Docker · Hosted (no local runtime)
- Credentials
- API key / credential required
- License
- Apache-2.0
- Last commit
41FMRS · D
The source clearly identifies this server as a GitHub integration for repositories, issues, pull requests, and workflows, with stdio and streamable HTTP transports. It does not enumerate tool identifiers, client compatibility, or detailed token permissions, so those fields are not inferred.
Strongest · Maintenance 10/20 Weakest · Security and permissions 7/20
Why each score
- Reliability 8/20
- The manifest exposes reviewable stdio OCI and streamable-HTTP entry points, making a basic startup path plausible. However, the version remains the unresolved ${VERSION} placeholder, and the supplied material contains no server-specific tests, CI, initialization-handshake evidence, tool-list evidence, or error-handling evidence. Reliability is therefore deducted and cannot exceed 12 under the static calibration.
- Security and permissions 7/20
- PAT and Authorization credentials are marked as secret, showing basic credential-injection locations. However, the server can manage repositories, issues, pull requests, and workflows, while the material does not establish least privilege, token scopes, data boundaries, confirmation for dangerous operations, or side-effect controls. No stated red-line security evidence was found.
- Maintenance 10/20
- The repository is not archived, declares Apache-2.0 licensing, and provides GitHub issue, Discord, and team ownership channels. However, there is no evidence here of commit history, release cadence, dependency updates, a security-response process, or server-specific maintenance. Stars and issue counts do not add points, so this receives a middling score.
- Documentation 7/20
- The README supplies cloud, self-hosting, SDK, and REST examples, plus documentation, community, and issue links. However, it primarily documents the Klavis platform or other integrations, not this GitHub official server: tool parameters, permission scopes, limits, costs, troubleshooting, and verifiable behavior are absent. The self-host example uses a Klavis github-mcp-server image and does not validate the manifest's GitHub-owned OCI package.
- Setup experience 9/20
- The manifest provides stdio and HTTP connection forms, and the README offers several integration entry points. Nevertheless, it lacks mainstream MCP-client configuration examples, explicit installation steps for this specific server, version-resolution guidance, platform compatibility details, and complete authentication instructions. The README's self-host path also does not match the target manifest, limiting setup confidence.
Static review · not runListed 2026-07-30
Read the FMRS scoring method →Fit and risk
What it can accessUses the networkChanges third-party account data
Not for
- Users who do not need GitHub integration
- Deployment environments that cannot provide a GitHub PAT or App token
- Use cases requiring specific tools or permissions not documented in the source
Required permissions
- Requires a GitHub Personal Access Token or App token
- stdio deployments must set GITHUB_PERSONAL_ACCESS_TOKEN
- Remote connections require an authentication token in the Authorization header
- The actual token permissions depend on the PAT or App token used
Risks and side effects
- Access tokens are secrets and should not be exposed
- Repository, issue, pull request, and workflow operations may change GitHub data or project state
- Overly broad token permissions may expand the actions available to the AI assistant
- Misinterpreted natural-language requests may cause unintended GitHub operations
Setup
Before you start
Runtime：Docker · Hosted (no local runtime)
GITHUB_PERSONAL_ACCESS_TOKEN
A GitHub personal access token (PAT) used to authenticate to the GitHub API; generate one in GitHub's Developer settings.
stdio: run the OCI image ghcr.io/github/github-mcp-server:${VERSION} and set the required GITHUB_PERSONAL_ACCESS_TOKEN environment variable. Remote: connect to https://api.githubcopilot.com/mcp/ and provide an Authorization header. The source does not provide a client-specific configuration example.
Check that it works
Run the server via the ghcr.io/github/github-mcp-server OCI image with GITHUB_PERSONAL_ACCESS_TOKEN set (stdio transport), or connect to the remote endpoint https://api.githubcopilot.com/mcp/ with an Authorization header; GitHub tools should appear in the client's tool list, and asking the assistant to list your repositories proves the connection.
Troubleshooting
- Verify that GITHUB_PERSONAL_ACCESS_TOKEN is set and valid
- For remote access, check that the Authorization header is present and uses the correct token
- Confirm that the token has the permissions required for the intended GitHub operation
- Check that the OCI image version variable has been replaced correctly
- Confirm that the client supports the selected stdio or streamable HTTP connection
Things to try
Once connected, you can ask your AI assistant things like:
- List all my open issues on GitHub
- Create a new issue titled Bug fix in my-repo
- Summarize the recent pull requests in my-repo
- Trigger the CI workflow on my-repo
Use cases
Manage GitHub repositories through natural language
Handle GitHub issues and pull requests
Manage GitHub workflows
Connect GitHub operations to an AI assistant
Overview
The GitHub MCP Server lets AI assistants manage GitHub repositories, issues, pull requests, and workflows through natural language. The server is provided by the GitHub upstream project and supports local containerized stdio execution and remote streamable HTTP access.
Similar servers
Context7
80 · B
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
NPM Sentinel MCP Server
79 · B
AI-powered NPM package analysis MCP server
MartinLoop MCP Server
79 · B
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub MCP Server
76 · B
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
More servers from this repository
Source revision 45c9f7da83d1 Data synced 2026-10-19 Read the FMRS scoring method