Skip to main content
mcpSource-backed
GitMCP logo

GitMCP Docs Server

Remote MCP server that turns any GitHub repository or GitHub Pages site into a documentation and code context source for AI coding assistants.

by idosal · submitted by oktofeesh1·added 2026-06-05·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://github.com/idosal/git-mcp, https://gitmcp.io
Brand
GitMCP
Brand domain
gitmcp.io
Brand asset source
brandfetch
Safety notes
Repository-specific endpoints reduce the chance of an agent querying the wrong project, while the dynamic endpoint relies on correct target selection., Verify generated code against the upstream project documentation and changelog before applying it to production systems., Use caution with private, unreleased, or embargoed repositories unless you self-host and have reviewed access controls.
Privacy notes
GitMCP may receive repository choices, documentation queries, tool calls, and surrounding prompts through the MCP client., The README states that the hosted service does not collect personal information or store queries, but teams should still review the current privacy posture before sending proprietary context., Self-hosting may be preferable for private repositories, regulated work, or sensitive customer projects.
Author
idosal
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

5 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

4 prerequisites to line up before setup.

0/4 ready
Configuration1Network & hosting2General15 minutes

Safety & privacy surface

Safety & privacy surface

3 safety and 3 privacy notes across 4 risk areas. Review closely: permissions & scopes, network access.

4 areas
  • SafetyNetwork accessRepository-specific endpoints reduce the chance of an agent querying the wrong project, while the dynamic endpoint relies on correct target selection.
  • SafetyData retentionVerify generated code against the upstream project documentation and changelog before applying it to production systems.
  • SafetyPermissions & scopesUse caution with private, unreleased, or embargoed repositories unless you self-host and have reviewed access controls.
  • PrivacyGeneralGitMCP may receive repository choices, documentation queries, tool calls, and surrounding prompts through the MCP client.
  • PrivacyData retentionThe README states that the hosted service does not collect personal information or store queries, but teams should still review the current privacy posture before sending proprietary context.
  • PrivacyGeneralSelf-hosting may be preferable for private repositories, regulated work, or sensitive customer projects.

Safety notes

  • Repository-specific endpoints reduce the chance of an agent querying the wrong project, while the dynamic endpoint relies on correct target selection.
  • Verify generated code against the upstream project documentation and changelog before applying it to production systems.
  • Use caution with private, unreleased, or embargoed repositories unless you self-host and have reviewed access controls.

Privacy notes

  • GitMCP may receive repository choices, documentation queries, tool calls, and surrounding prompts through the MCP client.
  • The README states that the hosted service does not collect personal information or store queries, but teams should still review the current privacy posture before sending proprietary context.
  • Self-hosting may be preferable for private repositories, regulated work, or sensitive customer projects.

Prerequisites

  • MCP client that supports remote MCP servers or an mcp-remote bridge.
  • GitHub repository owner and repository name, GitHub Pages site, or the dynamic GitMCP docs endpoint.
  • Network access to GitMCP and GitHub.
  • Team agreement on which repositories can be queried through a hosted MCP service.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
5 minutes
Difficulty
beginner
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "gitmcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://gitmcp.io/{owner}/{repo}"
      ]
    }
  }
}

About this resource

Content

GitMCP is a hosted, open-source MCP server that turns GitHub repositories and GitHub Pages sites into documentation and code-context sources for AI coding assistants. Instead of installing a project-specific MCP server, users point an MCP client at a GitMCP endpoint for the repository they are working with.

The project supports repository-specific endpoints, GitHub Pages endpoints, and a dynamic docs endpoint. Repository-specific endpoints are best when an assistant should stay focused on one project; the dynamic endpoint is useful when the assistant needs to choose among projects during a session.

Source Review

These sources were reviewed on 2026-06-05. Prefer the live repository and GitMCP site for current endpoint formats, supported clients, privacy language, self-hosting details, and remote MCP compatibility.

Features

  • Remote MCP access to live GitHub repository documentation and code context.
  • Repository-specific, GitHub Pages, and dynamic docs endpoint modes.
  • Setup examples for Cursor, Claude Desktop, Windsurf, VS Code, Cline, Highlight AI, Augment Code, and Msty.
  • Smart search over documentation and code sources.
  • Hosted zero-setup mode plus open-source self-hosting option.
  • PulseMCP top-pick listing as an external popularity signal.

Installation

For Claude Desktop-style clients that need a bridge, configure mcp-remote:

{
  "mcpServers": {
    "gitmcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://gitmcp.io/{owner}/{repo}"
      ]
    }
  }
}

For clients with native remote server support, add the repository-specific GitMCP endpoint directly. Replace {owner} and {repo} with the target GitHub project, or use the dynamic docs endpoint documented in the README.

Use Cases

  • Ground coding prompts in a library's current README, docs, and examples.
  • Ask an assistant to search a GitHub project before writing integration code.
  • Reduce hallucinated APIs for niche or rapidly changing packages.
  • Give Cursor, Claude Desktop, VS Code, or Windsurf repository-aware docs access without writing a custom MCP server.
  • Self-host a GitMCP-compatible service for private documentation workflows.

Safety and Privacy

Prefer repository-specific endpoints when a project should remain scoped to one codebase. Review all generated changes against the original documentation before committing them, especially for security-sensitive dependencies or production infrastructure.

Hosted remote MCP services can see requests routed through them. For private repositories, customer projects, unreleased APIs, or regulated work, review the current privacy language and consider self-hosting.

Duplicate Check

content/mcp/git-mcp-server.mdx covers the reference Git MCP server for local repository operations. This entry covers the separate idosal/git-mcp hosted documentation and code-context service for GitHub projects.

Source citations

Add this badge to your README

Show that GitMCP Docs Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/gitmcp-docs-server.svg)](https://heyclau.de/entry/mcp/gitmcp-docs-server)

How it compares

GitMCP Docs Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field

Remote MCP server that turns any GitHub repository or GitHub Pages site into a documentation and code context source for AI coding assistants.

Open dossier

Comprehensive Google Workspace MCP server and CLI for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Chat, Apps Script, Tasks, Contacts, and Custom Search workflows.

Open dossier

Official AWS Labs fully-managed remote MCP server providing up-to-date AWS documentation, code samples, agent skills, API and CloudFormation regional availability, and CDK/Amplify/Strands guidance over a hosted HTTP endpoint.

Open dossier

Official Microsoft Learn remote MCP server that gives AI agents real-time access to Microsoft documentation search, page fetch, and code sample search.

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersoktofeesh1oktofeesh1jaso0n0818JSONbored
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandGitMCP logoGitMCPGoogle Workspace MCP logoGoogle Workspace MCPAWS Labs logoAWS LabsMicrosoft logoMicrosoft
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthoridosalTaylor WilsdonAWS LabsMicrosoft
Added2026-06-052026-06-052026-06-212026-06-05
Platforms
Harness
Source repo
Safety notesRepository-specific endpoints reduce the chance of an agent querying the wrong project, while the dynamic endpoint relies on correct target selection. Verify generated code against the upstream project documentation and changelog before applying it to production systems. Use caution with private, unreleased, or embargoed repositories unless you self-host and have reviewed access controls.Google Workspace MCP can read, create, edit, send, share, delete, and manage data across Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Chat, Apps Script, Tasks, Contacts, and Search depending on configured scopes and tool tier. Start with the smallest useful tool tier and read-only or service-specific scopes where possible. Require human approval before sending email or chat messages, sharing Drive files, changing permissions, deleting content, editing business documents, or executing Apps Script workflows. Protect OAuth client secrets, refresh tokens, service account keys, and credential stores.This is a fully managed remote server hosted by AWS; it serves public AWS knowledge and requires no AWS account or credentials, so do not add AWS access keys for it. Because it is a remote server, your queries are sent to the AWS-hosted endpoint; only connect clients you trust to route requests there. Generative output about AWS APIs and resources can still be wrong; verify guidance against the official AWS documentation it links.The server is documentation-focused, but retrieved docs can still influence generated commands; review commands before running them. Remote MCP availability and schema can change, so verify client compatibility before depending on it in automation.
Privacy notesGitMCP may receive repository choices, documentation queries, tool calls, and surrounding prompts through the MCP client. The README states that the hosted service does not collect personal information or store queries, but teams should still review the current privacy posture before sending proprietary context. Self-hosting may be preferable for private repositories, regulated work, or sensitive customer projects.Emails, attachments, Drive files, calendar events, documents, spreadsheets, presentations, form responses, chat messages, contacts, search queries, OAuth tokens, and tool logs may be exposed to the MCP client and model. The repository describes a self-hosted data path to Google APIs, but prompts and tool results still flow through the chosen AI client and model provider. Review organization data retention, Workspace admin policies, OAuth app verification, and model-provider retention before connecting production accounts.Your documentation queries and search terms are sent over HTTPS to the AWS-hosted knowledge endpoint to retrieve content. The server returns public AWS documentation, code samples, and availability data; it does not read any private account data.Prompts and queries sent to a remote MCP server can reveal product names, architecture details, or error messages. Avoid sending customer identifiers or private tenant data when documentation search is enough.
Prerequisites
  • MCP client that supports remote MCP servers or an mcp-remote bridge.
  • GitHub repository owner and repository name, GitHub Pages site, or the dynamic GitMCP docs endpoint.
  • Network access to GitMCP and GitHub.
  • Team agreement on which repositories can be queried through a hosted MCP service.
  • Python 3.10 or newer and uv or uvx.
  • Google Cloud project with OAuth credentials.
  • Required Google Workspace APIs enabled for the services you plan to use.
  • OAuth consent, scopes, and redirect settings reviewed for the target account or organization.
  • An MCP client that supports remote HTTP MCP servers (or `uvx`/`fastmcp` to proxy the endpoint to stdio for clients that don't).
  • Outbound HTTPS access to the hosted endpoint `https://knowledge-mcp.global.api.aws`.
  • An MCP-compatible client that supports remote HTTP MCP servers.
  • Network access to learn.microsoft.com.
  • A Microsoft technology question where official Learn grounding is useful.
Install
npx mcp-remote https://gitmcp.io/{owner}/{repo}
uvx workspace-mcp --tool-tier core
uvx fastmcp run https://knowledge-mcp.global.api.aws
claude mcp add --transport http microsoft-learn https://learn.microsoft.com/api/mcp
Config
{
  "mcpServers": {
    "gitmcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://gitmcp.io/{owner}/{repo}"
      ]
    }
  }
}
{
  "mcpServers": {
    "google-workspace": {
      "command": "uvx",
      "args": ["workspace-mcp", "--tool-tier", "core"],
      "env": {
        "GOOGLE_OAUTH_CLIENT_ID": "YOUR_GOOGLE_OAUTH_CLIENT_ID",
        "GOOGLE_OAUTH_CLIENT_SECRET": "YOUR_GOOGLE_OAUTH_CLIENT_SECRET"
      }
    }
  }
}
{
  "mcpServers": {
    "aws-knowledge-mcp-server": {
      "url": "https://knowledge-mcp.global.api.aws",
      "type": "http"
    }
  }
}
{
  "mcpServers": {
    "microsoft-learn": {
      "url": "https://learn.microsoft.com/api/mcp"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.