No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by conikeec · MCP Server · ★ 347
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mcpr safe to install? View the security audit →
MCPR - Model Context Protocol for Rust A Rust implementation of Anthropic's Model Context Protocol (MCP), an open standard for connecting AI assistants to data sources and tools. ⚠️ IMPORTANT NOTICE: Version 0.2.0 has been yanked due to critical issues with the SSE transport implementation. Please use version 0.2.3 instead, which includes important fixes for client-server communication, message handling, and template generation. If you're already using 0.2.0, we strongly recommend upgrading to 0.2.3 to avoid potential issues. Examples View Demo on Github Tools MCP Client/Server Check out our GitHub Tools example for a complete implementation of an MCP client-server application that interacts with GitHub repositories. This example demonstrates how to build a client that can query repository READMEs and search for repositories, with support for multiple servers and client-server disconnection scenarios. It's a great starting point for understanding how to build your own MCP applications.
| Stars | 347 |
| Forks | 25 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69.7238306897131/100 |
| Open Issues | 13 |
| Last Updated | 2025-03-21 |
| Created | 2025-03-13 |
| Platforms | mcp, rust |
| Est. Tokens | ~38k |
Explore other popular mcp server tools:
mcpr is Model Context Protocol (MCP) implementation in Rust. It is categorized as a MCP Server with 347 GitHub stars.
mcpr is primarily written in Rust.
You can find installation instructions and usage details in the mcpr GitHub repository at github.com/conikeec/mcpr. The project has 347 stars and 25 forks, indicating an active community.
mcpr is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: