MCP Language Server

@isaacphi

リポジトリ

基本情報

カテゴリ

その他

ライセンス

BSD-3-Clause

トランスポート

stdio

作者

isaacphi

投稿者

Phil

MCP Language Server について

mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.

#ai #mcp#language-server-protocol#model-context-protocol #mcp-server

MCP Language Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "language-server": {
      "command": "go",
      "args": [
        "run",
        "github.com/isaacphi/mcp-language-server@latest",
        "--workspace",
        "/path/to/codebase/",
        "--lsp",
        "language-server-executable"
      ],
      "env": {
        "LOG_LEVEL": "INFO"
      }
    }
  }
}

MCP Language Server のツール

Retrieves the complete source code definition of any symbol (function, type, constant, etc.) from your codebase.

Locates all usages and references of a symbol throughout the codebase.

Provides diagnostic information for a specific file, including warnings and errors.

Display documentation, type hints, or other hover information for a given location.

Rename a symbol across a project.

Allows making multiple text edits to a file based on line numbers. Provides a more reliable and context-economical way to edit files compared to search and replace based edit tools.

概要

What is MCP Language Server?

MCP Language Server is an MCP server that runs and exposes a language server (LSP) to LLMs, enabling semantic code navigation such as definitions, references, rename, and diagnostics.

How to use MCP Language Server?

Install via go install github.com/isaacphi/mcp-language-server@latest, install a compatible language server (e.g., gopls, rust-analyzer, pyright), then configure your MCP client (e.g., Claude Desktop) with the binary path, --workspace and --lsp arguments, and any necessary environment variables.

Key features of MCP Language Server

Definition: retrieves complete source code definition of any symbol.
References: locates all usages and references of a symbol.
Diagnostics: provides diagnostic warnings and errors for a file.
Hover: displays documentation and type hints for a location.
Rename symbol: renames a symbol across the entire project.
Edit file: makes multiple text edits to a file by line numbers.

Use cases of MCP Language Server

Enabling LLMs to navigate and understand codebases semantically.
Automatically renaming symbols across a project.
Retrieving definitions and references for code comprehension.
Applying precise file edits via line-based text editing.
Getting diagnostics for error detection and correction.

よくある質問

What language servers are supported?

Go (gopls), Rust (rust-analyzer), Python (pyright), TypeScript (typescript-language-server), C/C++ (clangd), and any LSP server that communicates over stdio.

How do I install MCP Language Server?

Install Go, then run `go install github.com/isaacphi/mcp-language-server@latest`, then install your desired language server separately.

How do I configure MCP Language Server for Claude Desktop?

Add an entry to `claude_desktop_config.json` with the `command`, `args` including `--workspace` and `--lsp`, and any required environment variables.

Does MCP Language Server require any environment variables?

Yes, for some clients like Claude Desktop you may need to set PATH, GOPATH, GOCACHE, and GOMODCACHE to ensure the Go toolchain and language server are found.

Is MCP Language Server production-ready?

The README states it is beta software; users are encouraged to report issues.

「その他」の他のコンテンツ

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K