About Everforth GitHub MCP Server
Everforth GitHub MCP Server accesses GitHub through GraphQL for users working with GitHub data in Cursor. It keeps the access token in the MCP server configuration rather than giving it to Cursor Agent.
Key features
- 01Query GitHub through GraphQL
- 02Set the access token in configuration
- 03Customize builds with the Dockerfile
Use cases
- 01Access GitHub data in Cursor
- 02Work with GitHub ProjectV2 boards
MCP support
It acts as an MCP server for GraphQL access to GitHub. The README does not list specific tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
docker run -i --rm -e GITHUB_PERSONAL_ACCESS_TOKEN ikutani41/github-cli-mcp-serverGITHUB_PERSONAL_ACCESS_TOKENSecretLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEEverforth GitHub MCP Server
- この MCP server は github に graphql アクセスを投げるシンプルなもの
- Motivation
- アクセストークンをセキュアに扱う(Cursor Agent に与えない)
- 実は公式 MCPがまともに使えなかった & ProjectV2(カンバン)を使うならいずれにせよ graphql が必要
- パブリックイメージを置いておいたので Cursor に設定するだけで使える
- Dockerfile も置いてあるので、好きにカスタマイズしてビルドして使って OK
How to use
- Cursor の mcp.json に下記の
github-cliセクションを追加してください envの<PERSONAL_ACCESS_TOKEN>に自分の GitHub アクセストークンを貼ってください- Cursor を restart してください
- 必要に応じて、Rules にインストラクションを追加してください
{
"mcpServers": {
"github-cli": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GITHUB_PERSONAL_ACCESS_TOKEN",
"ikutani41/github-cli-mcp-server"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "<PERSONAL ACCESS TOKEN HERE>"
}
}
}
}
自分でビルドして使いたい場合
npm installdocker build -t {hoge}/github-cli-mcp-server -f Dockerfile .
Comments
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.