mcpls

io.github.bug-opsPublished by GitHub account bug-opsv0.9.1Updated Nov 3, 2026

Universal MCP to LSP bridge exposing language server code intelligence as MCP tools

VerifiedSTDIODesktop onlyDeveloper Tools AI & ML

Server details

Identifier: io.github.bug-ops/mcpls
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Nov 1, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account bug-ops for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.bug-ops%2Fmcpls.svg)](https://sourceweft.com/mcp/io.github.bug-ops%2Fmcpls?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Bridges MCP to language servers (LSP), giving an AI assistant IDE-style code intelligence: types, references, diagnostics and refactors.

What you can do: Inspect code: hover type information and documentation at a position or symbol name
Navigate: definitions, references, implementations, call and type hierarchies
Check code: real compiler diagnostics from the language server
Edit: rename and code-action edits returned for the client to apply
Explore: workspace symbol search across several language servers, formatting, inlay hints, selection and folding ranges
Manage: restart language servers on demand
When to use it: Useful when an AI coding agent should reason about a real project the way an IDE does — resolving types, finding every reference, or getting compiler diagnostics instead of guesses — especially in Rust, Python, Go or polyglot workspaces.
Requirements: Runs locally as a single Rust binary, installed via Cargo or the provided install scripts. Needs at least one language server installed for the target language (for example rust-analyzer). stdio by default; optional HTTP transport with Host and Origin allowlists. No credentials declared.

Before you install

Language servers execute code that ships with the workspace, and mcpls does not sandbox them; review the security documentation before pointing it at code you did not write. Rename and code-action tools return edits that the client applies, so changes to files can follow. Untrusted-workspace mode exists for analyzing code you do not trust.

Installation

In SourceWeft

Open mcpls in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mcpls

[Crates.io] [docs.rs] [CI] [codecov] [MSRV] [License]

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.

mermaid

flowchart LR    C["AI client"] <-->|MCP| M["mcpls"] <-->|LSP| S["rust-analyzer / pyright / gopls / ..."]

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:

Windows (PowerShell):

Or with Cargo:

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

Then ask about your code:

text

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, ...

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 unsafe code; 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

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.

Source: README.md at commit f13ba47

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.9.1LatestNov 3, 2026
v0.9.0Nov 1, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts