MCP Rust SDK

@jgmartin

Repository

Basic information

About MCP Rust SDK

An MCP client/server library for Rust

#mcp-sdk #rust-sdk #model-context-protocol

MCP Rust SDK config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

MCP Rust SDK tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Model Context Protocol (MCP) Rust SDK?

A Rust implementation of the Model Context Protocol (MCP), designed for seamless communication between AI models and their runtime environments. It is currently a work in progress and not ready for production use.

How to use Model Context Protocol (MCP) Rust SDK?

Add mcp_sdk_rs = "0.1.0" to your Cargo.toml. Then use the provided client and server examples: create a transport (WebSocket or stdio), set up mpsc channels, start a session, and make requests or serve. Both examples use Tokio for async execution.

Key features of Model Context Protocol (MCP) Rust SDK

Full implementation of MCP protocol specification
Multiple transport layers (WebSocket, stdio)
Async/await support using Tokio
Type-safe message handling
Comprehensive error handling
Zero-copy serialization/deserialization

Use cases of Model Context Protocol (MCP) Rust SDK

Network-based communication between AI models and remote runtime environments
Local process communication for command-line AI tools and development
Building custom MCP servers and clients in Rust
Integrating with WebSocket (WSS/WS) or stdio transports

Frequently asked questions

Is this SDK production‑ready?

No, the SDK is currently a work in progress and explicitly labeled as not ready for production use.

What transport layers does the SDK support?

It supports WebSocket (secure and standard) for network communication and stdio for local process communication.

What are the main runtime dependencies?

The SDK uses Tokio for async runtime and provides async/await support throughout.

How is error handling structured?

The SDK provides a comprehensive `Error` type that distinguishes protocol errors, transport errors, and other errors, enabling fine‑grained error handling.

What license does the SDK use?

The project is licensed under the MIT License. It was originally forked from [mcp-rust-sdk](https://github.com/Derek-X-Wang/mcp-rust-sdk).

Comments

More Developer Tools MCP servers

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Termany

thinkany-ai

Agent-Native Terminal

174

Rams

HSLA0001 Inc.

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag