mcpField
G
GitHub PR Comments MCP Server

GitHub PR Comments MCP Server

Local
github.com/shaileshahujaVersion Control3Updated 65w ago
Repository

About GitHub PR Comments MCP Server

A server for retrieving GitHub pull request comments, intended for clients and workflows that need review context. It returns comment text, file paths, line ranges, and replies in structured JSON.

Key features

  1. 01Fetch pull request comments
  2. 02Include paths, line ranges, and replies
  3. 03Return structured JSON
  4. 04Authenticate with a GitHub personal access token

Use cases

  1. 01Inspect review discussions for a repository pull request
  2. 02Provide comment context to a connected client

MCP support

Exposes the `get_pr_comments` tool to MCP clients. The tool accepts a repository owner, name, and pull request number.

#github#pull-request#comments#mcp#server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "github-pr": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

GitHub PR Comments MCP Server

smithery badge

This is a Model Context Protocol (MCP) server that fetches GitHub Pull Request comments using a GitHub personal access token.

GitHub PR Comments Server MCP server

Features

  • Fetches PR comments with file paths, line ranges, and replies
  • Uses GitHub API via Octokit
  • Implements MCP server with StdioServerTransport
  • Returns comments in a structured JSON format

Installation

Installing via Smithery

To install github-pr-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install github-pr-mcp --client claude
Installing Manually

  1. Clone the repository

  2. Install dependencies:

    npm install

  3. Create a .env file with your GitHub token:

    GITHUB_TOKEN=your_github_token_here

Usage

  1. Build the project:

    npm run build

  2. Run the server:

    npm start

    Or directly with a GitHub token:

    node dist/server.js your_github_token_here

  3. The server exposes a tool called get_pr_comments that accepts the following parameters:

    • owner: Repository owner (username or organization)
    • repo: Repository name
    • pull_number: Pull request number

Integration with Cursor

To integrate with Cursor, use the following command in Cursor's MCP server configuration:

node /path/to/dist/server.js your_github_token_here

Replace /path/to with the actual path to your project, and your_github_token_here with your GitHub personal access token.

Testing

A test client is included to verify the server functionality:

  1. Build the project:

    npm run build

  2. Run the test client:

    npm test

The test client will start the server, connect to it, and call the get_pr_comments tool with sample parameters.

Response Format

The server returns comments in the following format:

{
  "comments": [
    {
      "id": 123456789,
      "path": "src/example.js",
      "body": "This is a comment on a specific line",
      "line": 42,
      "start_line": 40,
      "user": {
        "login": "username"
      },
      "created_at": "2023-01-01T00:00:00Z",
      "replies": [
        {
          "id": 987654321,
          "body": "This is a reply to the comment",
          "user": {
            "login": "another-username"
          },
          "created_at": "2023-01-02T00:00:00Z"
        }
      ]
    }
  ]
}

Development

To run the server in development mode:

npm run dev

License

ISC

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.