#9191st of 142 in Agent frameworks and SDKs
rust-sdk
Official Rust SDK for building MCP servers and clients on tokio
- Stars
- 4.1k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Rust
3,290 on 22 Apr 20264,110 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
RMCP is the official Rust implementation of the Model Context Protocol, built on tokio and serde. It provides the `rmcp` core crate and `rmcp-macros`, whose `#[tool]`, `#[prompt]` and router macros generate tool and prompt handlers with JSON Schema 2020-12 schemas via schemars. It implements MCP 2026-07-28 and stays compatible with 2025-11-25 and earlier, and covers tools, resources, prompts, sampling, elicitation, tasks, and OAuth.
Who it is for: Rust developers building MCP servers or clients
Strengths
- Official SDK from the modelcontextprotocol org, tracking the 2026-07-28 spec and older versions
- Proc macros derive tool and prompt schemas from typed Rust structs
- Supports stdio, child-process and streamable HTTP transports, including stateless HTTP
- Client lifecycle modes allow discover, legacy initialize, or automatic fallback
Weaknesses
- 3.x release has breaking changes; upgrading from earlier versions requires the migration guide
- Requires tokio; no other async runtime is mentioned
- Library only; no ready-made server, so you write and build your own binary
- License is reported as NOASSERTION by detection, so terms need checking
What it needs
- no GPU
- Needs tokio, serde, schemars
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent frameworks and SDKs
See all 142| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 96 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 92 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 92 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitReact and Angular SDK for adding agent chat and generative UI to apps | 90 out of 100 |