Cargo MCP Server
Provides a suite of tools for running Cargo commands and interacting with Rust projects through AI agents. It enables automated builds, testing, linting, and documentation generation directly from any MCP-compatible client.
README
Cargo MCP Server
A Model Context Protocol (MCP) server that provides tools for running Cargo commands. This server allows AI agents to interact with Rust projects through Cargo, enabling automated builds, tests, documentation generation, and more.
Features
The server provides the following Cargo tools:
cargo_build- Build a Rust project with Cargocargo_test- Run tests for a Rust projectcargo_run- Run a Rust binarycargo_check- Check a project for errors without buildingcargo_clippy- Run Clippy lintercargo_fmt- Format Rust code using rustfmtcargo_doc- Generate documentationcargo_clean- Clean build artifactscargo_tree- Display dependency treecargo_update- Update dependencies in Cargo.lockcargo_bench- Run benchmarks
Installation
Prerequisites
- Python 3.8 or higher
- Rust and Cargo installed on your system
- Access to install Python packages
Install from source
- Clone this repository:
git clone <repository-url>
cd cargo-mcp
- Install the package:
pip install -e .
Usage
With Claude Desktop
Add the server to your claude_desktop_config.json:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"cargo-mcp": {
"command": "cargo-mcp"
}
}
}
With other MCP clients
The server can be used with any MCP-compatible client. Start the server using:
cargo-mcp
Testing with MCP Inspector
You can test the server using the MCP Inspector:
npx @modelcontextprotocol/inspector cargo-mcp
Tool Documentation
cargo_build
Build a Rust project with Cargo.
Parameters:
release(boolean, optional): Build in release mode with optimizationsfeatures(array, optional): List of features to activatetarget(string, optional): Build for the given target tripleworkspace_path(string, optional): Path to the workspace root (auto-detected if not provided)
cargo_test
Run tests for a Rust project.
Parameters:
test_name(string, optional): Name of specific test to runrelease(boolean, optional): Run tests in release modefeatures(array, optional): List of features to activateworkspace_path(string, optional): Path to the workspace root
cargo_run
Run a Rust binary.
Parameters:
bin_name(string, optional): Name of the binary to run (for multi-binary projects)args(array, optional): Arguments to pass to the binaryrelease(boolean, optional): Run in release modefeatures(array, optional): List of features to activateworkspace_path(string, optional): Path to the workspace root
cargo_check
Check a Rust project for errors without building it.
Parameters:
features(array, optional): List of features to activateworkspace_path(string, optional): Path to the workspace root
cargo_clippy
Run Clippy linter on a Rust project.
Parameters:
fix(boolean, optional): Automatically apply suggested fixesfeatures(array, optional): List of features to activateworkspace_path(string, optional): Path to the workspace root
cargo_fmt
Format Rust code using rustfmt.
Parameters:
check(boolean, optional): Check if files are formatted without modifying themworkspace_path(string, optional): Path to the workspace root
cargo_doc
Generate documentation for a Rust project.
Parameters:
open(boolean, optional): Open documentation in browser after generationno_deps(boolean, optional): Don't build documentation for dependenciesworkspace_path(string, optional): Path to the workspace root
cargo_clean
Clean build artifacts.
Parameters:
workspace_path(string, optional): Path to the workspace root
cargo_tree
Display dependency tree.
Parameters:
package(string, optional): Package to display tree forfeatures(array, optional): List of features to activateworkspace_path(string, optional): Path to the workspace root
cargo_update
Update dependencies in Cargo.lock.
Parameters:
package(string, optional): Specific package to updateworkspace_path(string, optional): Path to the workspace root
cargo_bench
Run benchmarks.
Parameters:
bench_name(string, optional): Name of specific benchmark to runfeatures(array, optional): List of features to activateworkspace_path(string, optional): Path to the workspace root
Project Structure Detection
The server automatically detects Rust projects by searching for Cargo.toml files. It walks up the directory tree from the current working directory to find the nearest Cargo.toml file and uses that directory as the workspace root.
You can override this behavior by providing the workspace_path parameter to any tool.
Error Handling
The server provides detailed error messages and logs for troubleshooting:
- Checks if Cargo is installed and available in PATH
- Validates that Cargo.toml exists in the target directory
- Captures both stdout and stderr from Cargo commands
- Provides detailed command execution information
Development
Setup
- Clone the repository
- Install development dependencies:
pip install -e ".[dev]"
Testing
Run tests using pytest:
pytest
Code Formatting
Format code using black:
black src/
Lint code using ruff:
ruff check src/
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For issues and questions:
- Create an issue on GitHub
- Check the MCP documentation for general MCP questions
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。