VERIFIED

Language

Safety: 65/100

0.0(0)

This MCP server exposes language server protocol (LSP) features like definitions, references, and diagnostics to LLMs, enhancing code navigation and understanding.

MCP ServersDevelopmentAI & LLMSearch & WebProductivityUtilitiesCloud & InfrastructureFreemium

Boost this tool

Subscribe to listing upgrades or segmented pushes.

Overview

This MCP server exposes language server protocol (LSP) features like definitions, references, and diagnostics to LLMs, enhancing code navigation and understanding.

This server is relatively safe for read-only operations. However, the ability to execute code indirectly through language server features introduces some risk. Ensure the underlying language server is up-to-date and the workspace is properly secured.

Performance depends heavily on the underlying language server and the size of the codebase. Large codebases may experience slower response times.

This server itself has no direct cost, but the LLM client using it may incur costs based on usage (e.g., token consumption).

HybridGo1,446 starsBSD-3-ClauseReleased 5/16/2025CI/CD

Connections & Capabilities

Connects To

GitHub

Capabilities

ReadWriteExec

Client Compatibility

Claude Desktop

full

Cursor

untested

Windsurf

untested

VS Code (Copilot)

untested

Quickstart

Claude Desktop Config

{
  "mcpServers": {
    "language-server": {
      "command": "/full/path/to/your/clone/mcp-language-server/mcp-language-server",
      "args": [
        "--workspace",
        "/path/to/workspace",
        "--lsp",
        "language-server-executable"
      ],
      "env": {
        "LOG_LEVEL": "DEBUG"
      }
    }
  }
}

Environment Variables

UPDATE_SNAPSHOTS

Tools (6)

safe

definition

Retrieves the source code definition of a symbol.

Read-only operation; no side effects.

safe

references

Locates all usages of a symbol throughout the codebase.

Read-only operation; no side effects.

safe

diagnostics

Provides diagnostic information (warnings, errors) for a file.

Read-only operation; no side effects.

safe

hover

Displays documentation or type hints for a given location.

Read-only operation; no side effects.

high

rename_symbol

Renames a symbol across a project.

Modifies code structure; potential for breaking changes.

high

edit_file

Applies multiple text edits to a file based on line numbers.

Modifies file content; potential for introducing errors.

Security

Auth Method

None

Data Locality

hybrid

Known Risks

!Exploits in underlying language servers could lead to arbitrary code execution.
!Information leakage through diagnostic messages or hover information.
!Incorrect workspace configuration could expose unintended files.
!Reliance on stdio for communication can be vulnerable to hijacking if not properly secured.

Safety Score

moderate risk

Positive

+Relies on established language server implementations (gopls, rust-analyzer, etc.)
+Primarily exposes read-oriented operations like definition lookup and finding references.
+Sandboxed by the underlying language server's capabilities.
+No direct filesystem access outside the workspace.

Risks

-Can execute code indirectly through language server features (e.g., code completion, refactoring).
-Potential for information leakage if the language server exposes sensitive data in diagnostics or hover information.
-Vulnerable to exploits in the underlying language server if not properly updated.
-Workspace access grants read permissions to the codebase.

Use Cases

Code Understanding

-Quickly understand unfamiliar codebases.
-Trace the execution flow of a program.
-Identify potential bugs or performance bottlenecks.

Code Refactoring

-Rename variables and functions safely.
-Extract code into reusable components.
-Apply code formatting rules consistently.

Code Generation

-Generate boilerplate code for new functions or classes.
-Automatically fix common coding errors.
-Create unit tests based on existing code.

Who Is This For?

Best For

LLMs needing to understand and manipulate codebases.
Automated code refactoring tools.
Code analysis and linting services.
Developers using LLMs to assist with coding tasks.

Not Ideal For

Environments with strict security requirements that prohibit code execution.
Small code snippets or isolated code examples where the overhead of a language server is not justified.
Real-time code editing where latency is critical.

Autonomy & Execution

Default ModeConfigurable

Destructive ToolsSandboxed

Autonomy level depends on the configured MCP client and the specific tools used. Exercise caution when enabling destructive tools like `rename_symbol` and `edit_file`.

StatelessYes

Retry LogicNone

ConcurrencySingle-threaded

Production Tip

Monitor language server logs for errors or performance issues, and ensure the language server is properly configured for the target workspace.

FAQ

What language servers are supported?

The server supports any language server that communicates over stdio, including gopls, rust-analyzer, pyright, typescript-language-server, and clangd.

How do I configure the workspace?

The `--workspace` argument specifies the root directory of the codebase.

How do I enable logging?

Set the `LOG_LEVEL` environment variable to `DEBUG`.

Why am I getting errors when using rename_symbol?

Ensure the language server is properly configured for your project and that all dependencies are resolved.

Can I use this server with multiple languages?

Yes, but you will need to configure a separate instance of the server for each language, pointing to the appropriate language server executable.

Is this server secure?

The server's security depends on the underlying language server and the configuration of the workspace. Keep your language servers updated and restrict workspace access to trusted code.

How do I contribute to this project?

Please submit small PRs and open Issues first for anything substantial. AI slop O.K. as long as it is tested, passes checks, and doesn't smell too bad.

Key Features

Development AI & LLM Search & Web Productivity Utilities Cloud & Infrastructure

Definition Lookup - Directly retrieve the source location of symbols to ensure context accuracy.

Reference Tracking - Identify all locations where a specific function or variable is used across the project.

Automated Renaming - Safely perform refactoring operations that maintain code integrity.

Diagnostic Reporting - Programmatically access compiler and linter errors to guide AI-based debugging.

MCP Integration - Standardized communication bridge between LLMs and existing Language Server Protocol servers.

Use Cases & Problems Solved

Use Cases

•Use when you need an AI agent to accurately jump to function definitions across a large codebase without relying on hallucinated file paths.
•Perfect for developers who want LLMs to perform automated refactoring tasks like renaming variables or methods with full semantic awareness.
•Ideal if you need to debug complex logic by having an AI agent automatically fetch and analyze compiler diagnostics and error messages.
•Great for onboarding to a new repository, allowing the AI to trace references and understand how specific modules interact with each other.
•Use when building autonomous coding assistants that require precise, protocol-backed code navigation capabilities to provide context-aware suggestions.

Problems Solved

✓Eliminates the inaccuracy of AI code analysis by providing real-time semantic data rather than heuristic-based guesses.
✓Reduces the manual effort required to manually trace code dependencies by automating the retrieval of symbol references.
✓Removes the ambiguity in LLM-generated code by allowing the model to verify definition locations before proposing changes.
✓Solves the context window limitation by allowing the AI to query specific language server protocol features on-demand instead of loading entire files.

Who It's For

Software engineers building custom MCP-compatible AI coding agentsOpen source maintainers creating intelligent CLI tools for repository navigationFull-stack developers integrating IDE-like intelligence into custom developer workflowsAutomation engineers building CI/CD pipelines that require semantic code analysisTechnical leads developing internal AI-powered code review tools

Metrics

Discovered2/14/2026

Reviews0

Saved By0 users

Related Tools

Language | AI Builder Hub Review & Alternatives | Flaex AI