GitHub MCP Server

47 tools. 25 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated:

25 can modify or destroy data
22 read-only
47 tools total

Community server · catalogue entry verified 01/07/2026

How to control GitHub MCP Server ↓

What GitHub MCP Server exposes to your agents

Read (22) Write / Execute (22) Destructive / Financial (3)
Critical Risk

The most dangerous GitHub MCP Server tools

25 of GitHub MCP Server's 47 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control GitHub MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and GitHub MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_card": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "add_card_to_column": {
    "limits": [
      {
        "counter": "add_card_to_column_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_file_contents": {
    "limits": [
      {
        "counter": "get_file_contents_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register GitHub MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON GITHUB →

Instant setup, no code required.

All 47 GitHub MCP Server tools

READ 22 tools
Read get_file_contents Get the contents of a file or directory from a GitHub repository Read get_issue Get details of a specific issue in a GitHub repository. Read get_project Get details about a specific project Read get_project_v2 Get details of a GitHub project V2 using GraphQL API Read get_pull_request Get details of a specific pull request Read get_pull_request_comments Get the review comments on a pull request Read get_pull_request_files Get the list of files changed in a pull request Read get_pull_request_reviews Get the reviews on a pull request Read get_pull_request_status Get the combined status of all status checks for a pull request Read list_column_cards List all cards in a project column Read list_commits Get list of commits of a branch in a GitHub repository Read list_issues List issues in a GitHub repository with filtering options Read list_organization_projects List all projects in a GitHub organization (at organization level, not repository level) Read list_organization_projects_v2 List projects V2 in a GitHub organization using GraphQL API Read list_project_columns List all columns in a project Read list_project_v2_items List items in a GitHub project V2 using GraphQL API Read list_projects List all projects in a GitHub repository Read list_pull_requests List and filter repository pull requests Read search_code Search for code across GitHub repositories Read search_issues Search for issues and pull requests across GitHub repositories Read search_repositories Search for GitHub repositories Read search_users Search for users on GitHub

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about GitHub MCP Server

Can an AI agent delete data through the GitHub MCP Server MCP server? +

Yes. The GitHub MCP Server server exposes 3 destructive tools including delete_card, delete_issue, delete_project_column. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through GitHub MCP Server? +

The GitHub MCP Server server has 20 write tools including add_card_to_column, add_issue_comment, add_item_to_project_v2. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach GitHub MCP Server.

How many tools does the GitHub MCP Server MCP server expose? +

47 tools across 3 categories: Destructive, Read, Write. 22 are read-only. 25 can modify, create, or delete data.

How do I enforce a policy on GitHub MCP Server? +

Register the GitHub MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every GitHub MCP Server tool call.

Deterministic rules across all 47 GitHub MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

47 GitHub MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.