The GitHub MCP Server connects AI tools directly to GitHub's platform. This gives AI agents, assistants, and chatbots the ability to read repositories and code files, manage issues and PRs, analyze code, and automate workflows. All through natural language interactions.
Use Cases
Repository Management: Browse and query code, search files, analyze commits, and understand project structure across any repository you have access to.
Issue & PR Automation: Create, update, and manage issues and pull requests. Let AI help triage bugs, review code changes, and maintain project boards.
CI/CD & Workflow Intelligence: Monitor GitHub Actions workflow runs, analyze build failures, manage releases, and get insights into your development pipeline.
Code Analysis: Examine security findings, review Dependabot alerts, understand code patterns, and get comprehensive insights into your codebase.
Team Collaboration: Access discussions, manage notifications, analyze team activity, and streamline processes for your team.
Built for developers who want to connect their AI tools to GitHub context and capabilities, from simple natural language queries to complex multi-step agent workflows.
Using the Go module
The Go module path is github.com/github/github-mcp-server/v2. Library consumers
must use this prefix in imports, for example
github.com/github/github-mcp-server/v2/pkg/github, and in go get commands.
No /v2 subdirectory is needed when building from a repository checkout.
The existing v2.0.0 tag predates this module-path correction and cannot be used
as a Go module. After this change is merged, a new release such as v2.0.1 must
be tagged from a commit containing the corrected module path. Until then,
consumers can use a pseudo-version from a commit containing this change.
Remote GitHub MCP Server
The remote GitHub MCP Server is hosted by GitHub and provides the easiest method for getting up and running. If your MCP host does not support remote MCP servers, don't worry! You can use the local version of the GitHub MCP Server instead.
Prerequisites
A compatible MCP host with remote server support (VS Code 1.101+, Claude Desktop, Cursor, Windsurf, etc.)
For quick installation, use one of the one-click install buttons above. Once you complete that flow, toggle Agent mode (located by the Copilot Chat text input) and the server will start. Make sure you're using VS Code 1.101 or later for remote MCP and OAuth support.
Alternatively, to manually configure VS Code, choose the appropriate JSON block from the examples below and add it to your host configuration:
Rovo Dev CLI - Installation guide for Rovo Dev CLI
Note: Each MCP host application needs to configure a GitHub App or OAuth App to support remote access via OAuth. Any host application that supports remote MCP servers should support the remote GitHub server with PAT authentication. Configuration details and support levels vary by host. Make sure to refer to the host application's documentation for more info.
Configuration
Toolset configuration
See Remote Server Documentation for full details on remote server configuration, toolsets, headers, and advanced usage. This file provides comprehensive instructions and examples for connecting, customizing, and installing the remote GitHub MCP Server in VS Code and other MCP hosts.
Note: When using OAuth with GitHub Enterprise with VS Code and GitHub Copilot, you also need to configure your VS Code settings to point to your GitHub Enterprise instance - see Authenticate from VS Code
To run the server in a container, you will need to have Docker installed.
Once Docker is installed, you will also need to ensure Docker is running. The Docker image is available at ghcr.io/github/github-mcp-server. The image is public; if you get errors on pull, you may have an expired token and need to docker logout ghcr.io.
Authentication. On github.com you don't need to create anything up front — the one-click buttons above log you in with OAuth on first use (a browser-based flow; the token is kept in memory only). The Docker buttons publish a fixed callback port (127.0.0.1:8085) so the container's login callback is reachable. See Local Server OAuth Login for how it works, headless/device-code fallback, and bringing your own OAuth or GitHub App (required for GitHub Enterprise Server and ghe.com).
Prefer a token? You can still authenticate with a GitHub Personal Access Token by setting GITHUB_PERSONAL_ACCESS_TOKEN instead (it takes precedence over OAuth). The MCP server can use many of the GitHub APIs, so enable the permissions that you feel comfortable granting your AI tools (to learn more about access tokens, please check out the documentation).
Handling PATs Securely
Environment Variables (Recommended)
To keep your GitHub PAT secure and reusable across different MCP hosts:
Store your PAT in environment variables
export GITHUB_PAT=your_token_here
Or create a .env file:
GITHUB_PAT=your_token_here
Protect your .env file
# Add to .gitignore to prevent accidental commits
echo ".env" >> .gitignore
Reference the token in configurations
# CLI usage
claude mcp add github -e GITHUB_PERSONAL_ACCESS_TOKEN=$GITHUB_PAT -- docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ghcr.io/github/github-mcp-server
# In config files (where supported)
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "$GITHUB_PAT"
}
Note: Environment variable support varies by host app and IDE. Some applications (like Windsurf) require hardcoded tokens in config files.
Token Security Best Practices
Minimum scopes: Only grant necessary permissions
repo - Repository operations
read:packages - Docker image access
read:org - Organization team access
Separate tokens: Use different PATs for different projects/environments
Regular rotation: Update tokens periodically
Never commit: Keep tokens out of version control
File permissions: Restrict access to config files containing tokens
chmod 600 ~/.your-app/config.json
GitHub Enterprise Server and Enterprise Cloud with data residency (ghe.com)
The flag --gh-host and the environment variable GITHUB_HOST can be used to set
the hostname for GitHub Enterprise Server or GitHub Enterprise Cloud with data residency.
For GitHub Enterprise Server, prefix the hostname with the https:// URI scheme. HTTPS is required and enforced: non-HTTPS hosts are refused so that credentials are never sent over cleartext (the only exception is a loopback host such as http://localhost for local development).
For GitHub Enterprise Cloud with data residency, use https://YOURSUBDOMAIN.ghe.com as the hostname.
For quick installation, use one of the one-click install buttons above. Once you complete that flow, toggle Agent mode (located by the Copilot Chat text input) and the server will start.
Install in GitHub Copilot on other IDEs (JetBrains, Visual Studio, Eclipse, etc.)
Add one of the following JSON blocks to your IDE's MCP settings.
Log in with OAuth (no token to create or store). On github.com the official image already includes the app credentials, so you provide none yourself: it runs a browser-based login on first use and keeps the resulting token in memory only. In Docker this needs a fixed callback port published to loopback so the container's login callback is reachable:
See Local Server OAuth Login for the native-binary flow (no fixed port needed), the headless/device-code fallback, GitHub Enterprise Server / ghe.com, and bringing your own OAuth or GitHub App.
Optionally, you can add a similar example (i.e. without the mcp key) to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with other host applications that accept the same format.
Note: Any host application that supports local MCP servers should be able to access the local GitHub MCP server. However, the specific configuration process, syntax and stability of the integration will vary by host application. While many may follow a similar format to the examples above, this is not guaranteed. Please refer to your host application's documentation for the correct MCP configuration syntax and setup process.
Build from source
If you don't have Docker, you can use go build to build the binary in the
cmd/github-mcp-server directory, and use the github-mcp-server stdio command with the GITHUB_PERSONAL_ACCESS_TOKEN environment variable set to your token. To specify the output location of the build, use the -o flag. You should configure your server to use the built executable as its command.
STDIO API requests identify the server as github-mcp-server/<version> and retain the upstream MCP client's name/version in parentheses when available. Control characters, quotes, backslashes and parentheses in client metadata are escaped so the HTTP header remains valid; ordinary names, versions, spaces and printable Unicode are preserved. Release builds keep their release version. Source and default Docker builds with revision metadata use vcs-<full-commit-sha>. The Docker publishing workflow preserves tag versions, including prereleases, and lets branch, pull-request and nightly builds use the linked source revision. The -dirty marker applies only when both the revision and modified state come from embedded VCS metadata, never to a valid, explicitly supplied main.commit. This is a VCS build identifier, not a release number.
Build the complete package with go build -o github-mcp-server ./cmd/github-mcp-server from a Git checkout to embed its VCS revision. For builds without VCS metadata, supply the actual release with -ldflags '-X main.version=<release>' or the full source revision with -ldflags '-X main.commit=<sha>'. Valid metadata is selected in this order: explicit release, explicit source revision, embedded VCS revision, then installed main-module version. Valid explicit revisions remain authoritative even if build-context filtering changes embedded VCS metadata. Missing or malformed candidates fall through to the next usable source. If none is available, STDIO still starts with the development label dev and emits a warning on stderr, leaving stdout available for the MCP protocol. Supply real release or revision metadata when version-specific attribution is needed.
The GitHub MCP Server supports enabling or disabling specific groups of functionalities via the --toolsets flag. This allows you to control which GitHub API capabilities are available to your AI tools. Enabling only the toolsets that you need can help the LLM with tool choice and reduce the context size.
Toolsets are not limited to Tools. Relevant MCP Resources and Prompts are also included where applicable.
This registers all tools from repos and issues toolsets, plus get_gist.
Important Notes:
Tools and toolsets can be used together
Read-only mode takes priority: write tools are skipped if --read-only is set, even if explicitly requested via --tools
Tool names must match exactly (e.g., get_file_contents, not getFileContents). Invalid tool names will cause the server to fail at startup with an error message
When tools are renamed, old names are preserved as aliases for backward compatibility. See Tool Renaming for details.
Using Toolsets With Docker
When using Docker, you can pass the toolsets as environment variables:
GitHub Git API related tools for low-level Git operations
governance
Repository governance tools for managing rulesets and custom properties at the repository, organization, and enterprise levels
issues
GitHub Issues related tools
labels
GitHub Labels related tools
notifications
GitHub Notifications related tools
orgs
GitHub Organization related tools
projects
GitHub Projects related tools
pull_requests
GitHub Pull Request related tools
repos
GitHub Repository related tools
secret_protection
Secret protection related tools, such as GitHub Secret Scanning
security_advisories
Security advisories related tools
stargazers
GitHub Stargazers related tools
users
GitHub User related tools
Additional Toolsets in Remote GitHub MCP Server
Toolset
Description
copilot
Copilot related tools (e.g. Copilot Coding Agent)
copilot_spaces
Copilot Spaces related tools
github_support_docs_search
Search docs to answer GitHub product and support questions
Tools
Repository tools expose output schemas and typed structuredContent when the negotiated MCP protocol version is a supported version 2026-07-28 or newer. Older clients, clients with an unknown protocol version, and clients omitting the version receive the existing content without an output schema or structured output. Unknown versions are not treated as supported merely because they sort after 2026-07-28.
For get_file_contents, directory results (including field projections) are structured arrays. File downloads and metadata-only responses use a content array of typed text, embedded-resource, or resource-link blocks, preserving status messages, text, base64 blobs, empty files, and download links. Text-only repository mutations such as starring and deletion also return a structured message; fork responses distinguish a repository reference from an in-progress message. Repository deletion still requires its existing confirmation flow before returning a completed result.
Structured repository results use compact DTOs rather than raw REST objects. Release lookups share the compact release shape with release listings; Git references retain the ref, object type, and SHA; annotated tags retain tag/message/tagger/target information; deletion commits retain SHA, message, authors, tree SHA, parent SHAs, and a human-facing html_url when available. Directory entries retain file metadata and useful HTML/download links, but omit API and hypermedia routing URLs even when those fields were requested in a projection. Legacy and unknown protocol versions retain the original text byte-for-byte; modern text-only JSON responses serialize the same compact DTO as structuredContent. Non-text resource blocks and tool errors retain their existing content behavior. Structured projections use the same sanitized and filtered source as the legacy formatter.
For get_repository_tree, list_gists, get_gist, create_gist, and update_gist, gist results retain file names, contents, sizes, language/type information, timestamps, visibility, and compact owner profiles, while omitting API/node and Git transport URLs. Tree entries omit their derivable API URLs. Create/update gist results contain the gist ID and HTML URL. Modern JSON text and structured content serialize the same compact result. Older or unknown protocol versions retain byte-for-byte legacy text without an output schema or structured content.
The issue metadata (list_issue_types, list_issue_fields), comment (add_issue_comment, update_issue_comment), dependency (issue_dependency_read, issue_dependency_write), and duplicate-detection (find_duplicate) tools provide typed outputSchema and structuredContent for negotiated supported protocol versions 2026-07-28 or newer. Older or unknown protocol versions retain the same text responses without these fields. Tool errors do not return structured content. Dependency and duplicate-detection tools retain their existing feature gates.
For negotiated supported protocol versions 2026-07-28 or newer, the consolidated Actions tools (actions_list, actions_get, actions_run_trigger) return structured objects with a method discriminant and a method-specific typed field; JSON text contains the same compact projection. Workflow, job, and artifact projections omit API/hypermedia URLs while retaining browser links and useful identifiers, states, timestamps, and usage durations. Run usage lists billable runner environments in deterministic name order. Older and unknown-protocol text responses remain unchanged; get_job_logs retains its typed content, URL, or failed-job collection variants.
Actions
actions_get - Get details of GitHub Actions resources (workflows, workflow runs, jobs, and artifacts)
OAuth Challenge Scopes: repo
method: The method to execute (string, required)
owner: Repository owner (string, required)
repo: Repository name (string, required)
resource_id: The unique identifier of the resource. This will vary based on the "method" provided, so ensure you provide the correct ID:
Provide a workflow ID or workflow file name (e.g. ci.yaml) for 'get_workflow' method.
Provide a workflow run ID for 'get_workflow_run', 'get_workflow_run_usage', and 'get_workflow_run_logs_url' methods.
Provide an artifact ID for 'download_workflow_run_artifact' method.
Provide a job ID for 'get_workflow_job' method.
(string, required)
actions_list - List GitHub Actions workflows in a repository
OAuth Challenge Scopes: repo
method: The action to perform (string, required)
owner: Repository owner (string, required)
page: Page number for pagination (default: 1) (number, optional)
perPage: Results per page for pagination (default: 30, max: 100) (number, optional)
repo: Repository name (string, required)
resource_id: The unique identifier of the resource. This will vary based on the "method" provided, so ensure you provide the correct ID:
Do not provide any resource ID for 'list_workflows' method.
Provide a workflow ID or workflow file name (e.g. ci.yaml) for 'list_workflow_runs' method, or omit to list all workflow runs in the repository.
Provide a workflow run ID for 'list_workflow_jobs' and 'list_workflow_run_artifacts' methods.
(string, optional)
workflow_jobs_filter: Filters for workflow jobs. ONLY used when method is 'list_workflow_jobs' (object, optional)
workflow_runs_filter: Filters for workflow runs. ONLY used when method is 'list_workflow_runs' (object, optional)
inputs: Inputs the workflow accepts. Only used for 'run_workflow' method. (object, optional)
method: The method to execute (string, required)
owner: Repository owner (string, required)
ref: The git reference for the workflow. The reference can be a branch or tag name. Required for 'run_workflow' method. (string, optional)
repo: Repository name (string, required)
run_id: The ID of the workflow run. Required for all methods except 'run_workflow'. (number, optional)
workflow_id: The workflow ID (numeric) or workflow file name (e.g., main.yml, ci.yaml). Required for 'run_workflow' method. (string, optional)
get_job_logs - Get GitHub Actions workflow job logs
OAuth Challenge Scopes: repo
failed_only: When true, gets logs for all failed jobs in the workflow run specified by run_id. Requires run_id to be provided. (boolean, optional)
job_id: The unique identifier of the workflow job. Required when getting logs for a single job. (number, optional)
owner: Repository owner (string, required)
repo: Repository name (string, required)
return_content: Returns actual log content instead of URLs (boolean, optional)
run_id: The unique identifier of the workflow run. Required when failed_only is true to get logs for all failed jobs in the run. (number, optional)
tail_lines: Number of lines to return from the end of the log (number, optional)
Code Quality
get_code_quality_finding - Get code quality finding
OAuth Challenge Scopes: repo
findingNumber: The number of the finding. (number, required)
owner: The owner of the repository. (string, required)
repo: The name of the repository. (string, required)
Code Security
get_code_scanning_alert - Get code scanning alert
OAuth Challenge Scopes: security_events
alertNumber: The number of the alert. (number, required)
owner: The owner of the repository. (string, required)
repo: The name of the repository. (string, required)
list_code_scanning_alerts - List code scanning alerts
OAuth Challenge Scopes: security_events
owner: The owner of the repository. (string, required)
page: Page number for pagination (min 1) (number, optional)
perPage: Results per page for pagination (min 1, max 100) (number, optional)
ref: The Git reference for the results you want to list. (string, optional)
repo: The name of the repository. (string, required)
severity: Filter code scanning alerts by severity (string, optional)
state: Filter code scanning alerts by state. Defaults to open (string, optional)
tool_name: The name of the tool used for code scanning. (string, optional)
Context
get_me - Get my user profile
MCP App UI: ui://github-mcp-server/get-me
No parameters required
get_team_members - Get team members
OAuth Challenge Scopes: read:org
org: Organization login (owner) that contains the team. (string, required)
team_slug: Team slug (string, required)
get_teams - Get teams
OAuth Challenge Scopes: read:org
user: Username to get teams for. If not provided, uses the authenticated user. (string, optional)
ui_get - Get UI data
OAuth Challenge Scopes: repo, read:org
method: The type of data to fetch (string, required)
owner: Repository owner (required for all methods) (string, required)
repo: Repository name (required for labels, assignees, milestones, branches, issue fields, reviewers) (string, optional)
Copilot
assign_copilot_to_issue - Assign Copilot to issue
OAuth Challenge Scopes: repo
base_ref: Git reference (e.g., branch) that the agent will start its work from. If not specified, defaults to the repository's default branch (string, optional)
custom_instructions: Optional custom instructions to guide the agent beyond the issue body. Use this to provide additional context, constraints, or guidance that is not captured in the issue description (string, optional)
issue_number: Issue number (number, required)
owner: Repository owner (string, required)
repo: Repository name (string, required)
request_copilot_review - Request Copilot review
OAuth Challenge Scopes: repo
owner: Repository owner (string, required)
pullNumber: Pull request number (number, required)
repo: Repository name (string, required)
Copilot Issue Intents
assign_copilot_to_issue_with_intent - Assign Copilot to issue with intent
OAuth Challenge Scopes: repo
base_ref: Git reference (e.g., branch) that the agent will start its work from. If not specified, defaults to the repository's default branch. Ignored when is_suggestion is true (string, optional)
confidence: How confident you are in this choice. 'HIGH' for clear signal or explicit user request, 'MEDIUM' for reasonable inference with some ambiguity, 'LOW' for best guess with limited signal. (string, required)
custom_instructions: Optional custom instructions to guide the agent beyond the issue body. Ignored when is_suggestion is true (string, optional)
is_suggestion: If true, records a pending Copilot assignment intent rather than launching the agent. Approval later supplies the launch context; base_ref and custom_instructions are ignored in this case. (boolean, required)
issue_number: Issue number (number, required)
owner: Repository owner (string, required)
rationale: One concise sentence explaining what specifically about the issue led to choosing Copilot. State the concrete signal (e.g. 'Well-scoped task with clear acceptance criteria'). (string, required)
repo: Repository name (string, required)
Dependabot
get_dependabot_alert - Get dependabot alert
OAuth Challenge Scopes: security_events
alertNumber: The number of the alert. (number, required)
owner: The owner of the repository. (string, required)
repo: The name of the repository. (string, required)
list_dependabot_alerts - List dependabot alerts
OAuth Challenge Scopes: security_events
after: Cursor for pagination. Use the cursor from the previous response. (string, optional)
owner: The owner of the repository. (string, required)
perPage: Results per page for pagination (min 1, max 100) (number, optional)
repo: The name of the repository. (string, required)
severity: Filter dependabot alerts by severity (string, optional)
state: Filter dependabot alerts by state. Defaults to open (string, optional)
body: Comment content (required for 'add', 'reply', and 'update' methods) (string, optional)
commentNodeID: The Node ID of the discussion comment (required for 'reply', 'update', 'delete', 'mark_answer', and 'unmark_answer' methods). For 'reply', this is the top-level comment to reply to; GitHub Discussions only support one level of nesting. (string, optional)
discussionNumber: Discussion number (required for 'add' and '
More MCP Servers
MCP Servers
Context7 MCP
MCP server by Upstash that pulls up-to-date library documentation straight into Claude context — no more hallucinated APIs, always current docs.
Official MCP server for structured chain-of-thought reasoning — gives Claude a scratchpad to think through complex problems step by step before answering.