What does protoc-gen-go-mcp generate?
It generates Go source code implementing a Model Context Protocol server that wraps gRPC services defined in a .proto file.
@juliendoutre
基本情報
A Go protoc plugin to implement MCP servers for gRPC services.
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
protoc-gen-go-mcp is a protoc plugin that generates Go Model Context Protocol (MCP) server code from protobuf service definitions. It integrates with the protobuf ecosystem and gRPC to produce MCP tools that can be used by LLM clients.
Install via Homebrew (brew tap juliendoutre/protoc-gen-go-mcp and brew install protoc-gen-go-mcp), then run protoc with the --go-mcp_out flag after installing protoc, protoc-gen-go, and protoc-gen-go-grpc. An example invocation is provided: protoc ./example/api.proto --go_out=./example/ --go-grpc_out=./example/ --go-mcp_out=./example/. The generated MCP server can be run and configured in an IDE like Cursor by adding its command to the MCP configuration file.
It generates Go source code implementing a Model Context Protocol server that wraps gRPC services defined in a .proto file.
You need protoc, protoc-gen-go, protoc-gen-go-grpc, and protoc-gen-go-mcp installed. The generated code uses standard Go and gRPC packages; no additional MCP libraries are mentioned beyond the example.
On macOS you can use Homebrew: `brew tap juliendoutre/protoc-gen-go-mcp` then `brew install protoc-gen-go-m

DrUrls audits websites for SEO, and its MCP server lets Claude, ChatGPT, Claude Code, Cursor or VS Code work with those audits directly: list your sites with their latest score and grade, read each issue across SEO, perf

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

コメント