mcpField
G
Github Mcp Server Review Tools

Github Mcp Server Review Tools

Local
github.com/wjessupVersion Control22Updated 82w ago
Repository

About Github Mcp Server Review Tools

An extended GitHub MCP server that adds tools for pull request review and review comment operations. It suits developers who want AI assistants to work with PR review data.

Key features

  1. 01Get a specific pull request review
  2. 02Get pull request review comments
  3. 03Runs on Node.js with yarn
  4. 04Docker build option, reported as untested

Use cases

  1. 01Letting an AI assistant read review content for a pull request
  2. 02Using the server in Cursor with a GitHub personal access token

MCP support

This project is an MCP server that exposes pull request review tools to MCP clients.

#github#mcp#server#review#tools

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-mcp-server-review-tools": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "build"
      ]
    }
  }
}
Run commanddocker run -i --rm build

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
ocibuild

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

Tools:

tools: [
      {
        name: "get_pull_request_review",
        description: "Get a specific pull request review",
        inputSchema: zodToJsonSchema(pullRequestReviews.GetPullRequestReviewSchema)
      },
      {
        name: "get_pull_request_comment",
        description: "Get a specific pull request review comment",
        inputSchema: zodToJsonSchema(pullRequestComments.GetPullRequestCommentSchema)
      },
      {
        name: "reply_to_pull_request_comment",
        description: "Add a reply to a specific pull request review comment",
        inputSchema: zodToJsonSchema(pullRequestComments.ReplyToPullRequestCommentSchema)
      },
      {
        name: "resolve_pull_request_review_thread",
        description: "Mark a pull request review thread as resolved",
        inputSchema: zodToJsonSchema(pullRequestReviews.ResolvePullRequestReviewThreadSchema)
      },
      {
        name: "check_pull_request_review_resolution",
        description: "Check if all threads in a pull request review are resolved",
        inputSchema: zodToJsonSchema(pullRequestReviews.CheckPullRequestReviewResolutionSchema)
      },
      {
        name: "get_pull_request_review_threads",
        description: "Get the threads in a specific pull request review",
        inputSchema: zodToJsonSchema(pullRequestReviews.GetPullRequestReviewThreadsSchema)
      },
      {
        name: "get_pull_request_threads",
        description: "Get all review threads for a pull request in a single call",
        inputSchema: zodToJsonSchema(pullRequestReviews.GetPullRequestThreadsSchema)
      },
      {
        name: "get_pull_request_thread",
        description: "Get a single pull request review thread with complete comment details",
        inputSchema: zodToJsonSchema(pullRequestReviews.GetPullRequestThreadSchema)
      }
    ],

install manually:

Yarn && Yarn start

Install into cursor:

{
  "mcpServers": {
    "github-pr-review-tools": {
      "command": "node",
      "args": ["~/Code/github-server-only/dist/index.js"], #put your repo location
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": <your code here>
      }
    }
  }
}

Build

Docker build: (haven't tested)

docker build -t mcp/github -f src/github/Dockerfile .

License

MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

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.