mcpls MCP server
Commit Nov 15, 2026Exposes language server intelligence like type information, references, and diagnostics as MCP tools for AI coding agents.
Also known as bug-ops/mcpls
- Stars
- 83
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.10.0
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is mcpls MCP?
mcpls exposes language server intelligence like type information, references, and diagnostics as MCP tools for AI coding agents.
Summary generated from the project's README
About mcpls MCP server
mcpls acts as a bridge between the Model Context Protocol and the Language Server Protocol to provide AI coding agents with deep technical insights. By running existing language servers like rust-analyzer, pyright, or gopls, it exposes 31 specific MCP tools that allow an AI client to access type information, references, diagnostics, and refactoring capabilities. This setup enables an AI to reason about a codebase with the same precision as a professional integrated development environment.
Developers can install the server via curl, PowerShell, or Cargo and connect it to clients such as Claude Code. While Rust projects work without extra setup, other languages may require configuration. The server supports multiple language servers running concurrently in a polyglot project and offers an untrusted-workspace mode for safer analysis. It uses stdio by default but also supports HTTP transport with allowlists for more complex environments.
What you can do with it
- 1Retrieve specific type informationAn AI agent can identify the exact return type of a function using hover tools.
- 2Locate code referencesA developer can ask the agent to find every instance where a specific error or symbol is handled.
- 3Perform codebase refactoringThe agent can use compiler-backed tools to execute renames and code-action edits.
- 4Search polyglot workspacesUsers can search for symbols across different programming languages within a single project.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 12, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubmcpls
Give your AI coding agent a compiler's understanding of your code.
mcpls is a bridge between the Model Context Protocol (MCP) and the Language Server Protocol (LSP). It runs the language servers for your project (rust-analyzer, pyright, gopls, and others) and exposes their type information, references, diagnostics and refactoring as 31 MCP tools, so an AI client reasons about code the way an IDE does.
flowchart LR
C["AI client"] <-->|MCP| M["mcpls"] <-->|LSP| S["rust-analyzer / pyright / gopls / ..."]
Documentation
The full documentation is the mcpls book: https://bug-ops.github.io/mcpls/
| Topic | Chapter |
|---|---|
| Install and first run | Installation |
| Connect Claude Code or another client | Connect an AI Client |
| Configure language servers | Configuration |
| All 31 tools | Tools Overview |
| Something does not work | Troubleshooting |
| HTTP transport and allowlists | Transports |
| Security model and untrusted workspaces | Security and Trust |
| Every flag and config key | Reference |
Installation
Linux and macOS:
curl -fsSL https://raw.githubusercontent.com/bug-ops/mcpls/main/scripts/install.sh | sh
Windows (PowerShell):
irm https://raw.githubusercontent.com/bug-ops/mcpls/main/scripts/install.ps1 | iex
Or with Cargo:
cargo install mcpls
Prebuilt archives for Linux, macOS and Windows (x86_64 and aarch64) with SHA256 checksums and build-provenance attestations are on GitHub Releases.
mcpls is also listed in the official MCP Registry as io.github.bug-ops/mcpls (cargo package, stdio transport), so registry-aware clients can discover it there. The listing installs the same crate as cargo install mcpls.
You also need at least one language server, for example rustup component add rust-analyzer. See Installation for other methods and servers.
Quick start
Register mcpls with Claude Code:
claude mcp add --scope user mcpls -- mcpls
Then ask about your code:
You: What is the return type of process_request?
Claude: [get_hover] It returns Result<Response, ApiError>.
You: Find everywhere ApiError::Timeout is handled.
Claude: [get_references] Found 4 matches: src/handlers/api.rs:89, ...
Rust projects need no configuration. Other languages and clients are covered in the book.
Features
- Type information and documentation at any position
- Cross-references, definitions, implementations across the whole workspace
- Real diagnostics from the compiler, not guesses
- Rename and code-action edits returned for the client to apply
- Call and type hierarchies, formatting, inlay hints, selection and folding ranges
- Workspace symbol search across every language server of a polyglot project, with each symbol tagged by its server
- Address code by symbol name as well as by position, and restart language servers on demand
- Several language servers at once, started concurrently and stopped with mcpls, with graceful degradation when one fails
- stdio by default, optional HTTP transport with Host and Origin allowlists and resource subscriptions
- Untrusted-workspace mode for analyzing code you do not trust
- Single Rust binary, no runtime dependencies, no
unsafecode; release archives carry build-provenance attestations
Security
Language servers run code that comes with the workspace, and mcpls does not sandbox them. Read SECURITY.md and the Security and Trust chapter before pointing mcpls at code you did not write.
Agent skill
skills/mcpls is a packaged Agent Skill that teaches an AI coding agent to install, configure and run mcpls.
Development
cargo build
cargo nextest run --workspace --all-features
Requires Rust 1.99 or later (edition 2024). The book lives in book/ and is built with mdBook. See CONTRIBUTING.md.
Community
Participation is governed by the Code of Conduct. Accessibility of the output and documentation is described in ACCESSIBILITY.md.
License
Dual-licensed under Apache 2.0 or MIT at your option.
mcpls MCP questions
What does mcpls do?
It acts as a bridge between the Model Context Protocol and the Language Server Protocol, allowing AI clients to use language server features like type information and refactoring.
Is mcpls secure for untrusted code?
Language servers run code from the workspace and mcpls does not sandbox them, so you should read the security documentation before using it on untrusted code.
Does it support multiple languages?
Yes, it can run several language servers concurrently, such as rust-analyzer, pyright, and gopls.