io.github.xieyuschen/gopls-mcp MCP Server
io.github.xieyuschen/gopls-mcp
Semantic code analysis for Go using gopls—compiler-level type checking and navigation for AI agents.
What is the io.github.xieyuschen/gopls-mcp MCP server?
gopls-mcp is an MCP server that delivers type-checker-level semantic analysis for Go code directly to LLMs. Unlike text-based search, it resolves Go's type system with compiler precision, enabling accurate interface satisfaction checks, cross-package identity resolution, and scope analysis. It reduces tool calls by 2–4× on semantic tasks compared to grep-based approaches.
gopls-mcp gives AI agents access to gopls' semantic understanding of Go codebases. It excels at semantic tasks like finding all concrete types implementing an interface, tracing call hierarchies, and mapping package dependencies. For simple same-file lookups, plain text search remains equally effective; gopls-mcp shines on complex, type-aware navigation.
How to install io.github.xieyuschen/gopls-mcp
Copy-paste configuration for popular MCP clients.
No machine-readable install method is published for this server in the registry. Check the repository or website for setup instructions.
Tools & capabilities
Tools this server exposes to the agent.
Type-aware code navigation— Resolve Go's type system to find definitions, references, and implementations with compiler precision.Interface implementation discovery— Find all concrete types that satisfy a given interface.Call hierarchy tracing— Map function call chains and dependencies across packages.Package dependency analysis— Understand and navigate cross-package relationships and imports.Scope and shadowing resolution— Correctly resolve variable and type identities accounting for Go's scoping rules.
Use cases
- Find all concrete types implementing a specific interface in a large codebase
- Trace call hierarchies to understand how functions are invoked across packages
- Navigate to definitions and references with full type-system awareness, not just text matching
- Map package dependencies and understand cross-package relationships
- Resolve shadowed variables and scopes correctly for accurate code understanding
io.github.xieyuschen/gopls-mcp MCP server FAQ
gopls-mcp is an MCP server that exposes gopls (the Go language server) to AI agents, providing compiler-level semantic analysis instead of text-based search. It resolves Go's type system accurately for tasks like finding interface implementations and tracing call hierarchies.
Yes, gopls-mcp is open-source and free to use. It is licensed under the BSD license, the same as its upstream gopls source.
For Claude Code, use `/plugin marketplace add https://github.com/xieyuschen/gopls-mcp.git` followed by `/plugin install gopls-mcp`. For Codex, use `codex plugin marketplace add` and `codex plugin add gopls-mcp`. The plugin automatically installs the binary.
Yes. On Linux/macOS, run `curl -sSL https://gopls-mcp.org/install.sh | bash`. On Windows (PowerShell), run `irm https://gopls-mcp.org/install.ps1 | iex`. Then follow the per-client setup at https://gopls-mcp.org/quick-start.
Use gopls-mcp for semantic tasks: finding interface implementations, tracing call hierarchies, and mapping package dependencies. For simple same-file lookups, plain text search is equally effective and has less overhead.
No, gopls-mcp does not require authentication. It operates on your local Go codebase using the gopls language server.
README (reference)
Source of truth, from the repository.
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.
Related MCP servers

io.github.xingbofeng/skill-deck
Expose local Agent Skills as adapter tools, MCP resources, MCP tools, and share artifacts.

NovelAI Image MCP
NovelAI image generation as MCP tools: txt2img, img2img, inpaint, upscale, Director, ControlNet.

io.github.xinxinhenaixin/emailfinder-mcp
Find verified professional emails by name, domain, LinkedIn, or role.

Xitoring
Connect AI assistants to Xitoring monitoring: servers, uptime, incidents, metrics, SSL, and alerts.

Search rangefind static indexes: full-text, geo, autocomplete, facets - no server, just files.

ReceiptRail
Read-only on-chain receipt check for x402 payments; confirm settlement before trusting a tx.