mcpField
G
gopls-mcp

gopls-mcp

Local
github.com/xieyuschenDeveloper Tools60Updated 1w ago

About gopls-mcp

gopls-mcp is an MCP server that brings gopls semantic analysis for Go to AI agents, covering navigation, definitions and references. It targets Go developers who need type-checker-level precision, and is a community fork of gopls rather than an official Go product.

Key features

  1. 01Type-aware Go code analysis built on gopls
  2. 02Finding all concrete types implementing an interface
  3. 03Tracing call hierarchies across code
  4. 04Mapping package dependencies
  5. 05Plugin installs for Claude Code and Codex

Use cases

  1. 01Finding interface implementations in large Go projects
  2. 02Letting coding agents trace function call chains
  3. 03Mapping cross-package dependencies

MCP support

gopls-mcp runs as an MCP server and exposes gopls semantic analysis results as tools for navigation, definition lookup and reference queries.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

gopls-mcp

Give your AI Agent the compiler's brain, not a text searcher.

Documentation: https://gopls-mcp.org

gopls-mcp delivers type-checker-level semantic analysis directly to your LLM. Unlike text search, it resolves Go's type system — interface satisfaction, cross-package identity, and shadowed scopes — with the same precision as the compiler.

Where it pays off most is on semantic tasks: finding all concrete types that implement an interface, tracing call hierarchies, and mapping package dependencies. A benchmark over 11 tasks shows gopls-mcp uses 2–4× fewer tool calls and finishes faster than grep-based navigation on those tasks. For simple same-file lookups, plain bash/grep remains equally effective and carries less overhead.

Install

Claude Code (plugin — recommended)
/plugin marketplace add https://github.com/xieyuschen/gopls-mcp.git
/plugin install gopls-mcp

The plugin automatically installs the binary and injects the routing skill — no manual setup required.

Codex (plugin — recommended)
codex plugin marketplace add https://github.com/xieyuschen/gopls-mcp.git
codex plugin add gopls-mcp
Manual install (all clients)

Linux / macOS:

curl -sSL https://gopls-mcp.org/install.sh | bash

Windows (PowerShell):

irm https://gopls-mcp.org/install.ps1 | iex

Then follow the per-client setup at https://gopls-mcp.org/quick-start.

Contribute

The project is actively developing, and feel free to raise PRs or issues if you find anything to improve. AI generated code will also be accepted but do remember to narrow the change to a specific feature for reviewer to quickly review them.

Disclaimer: gopls-mcp is a fork of gopls and is a community-driven project. It is not an official Go team product and is not affiliated with or endorsed by Google LLC. This project is licensed under the same BSD license as its upstream source.

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.