YAMS (Yet Another MCP Server)
A batteries-included MCP server providing common coding-agent tools like web search, page fetching, file system access, shell command execution, and Git integration, built in Python with a local-first, Unix-style philosophy.
README
YAMS
Yet Another MCP Server
YAMS is a batteries-included MCP server that provides the common tools most coding agents need:
- Web search
- Fetching and parsing web pages
- File system access
- Shell command execution
- Git integration
- Basic utility tools
Built in Python. Run with uv.
No Electron. No Docker required. No enterprise platform. Just tools.
Why?
Every agent stack ends up rebuilding the same MCP tools:
- search
- fetch
- grep
- git
- run commands
- read/write files
YAMS packages the boring, standard functionality into a single MCP server that works well locally, in CI, or on remote hosts.
The goal is not to be clever.
The goal is to be useful.
Features
- Fast startup
- Single-process architecture
- Async Python implementation
- Designed for local-first workflows
- Works well with Claude Code-style agents
- Easy to extend with custom tools
- Sensible defaults
- Minimal configuration
Installation
From GitHub
uv tool install git+https://github.com/carlosroman/yams.git
Or run without installing:
uvx --from git+https://github.com/carlosroman/yams.git yams
Quick Start
Start the server:
uvx yams
Example MCP client configuration:
{
"mcpServers": {
"yams": {
"command": "uvx",
"args": ["yams"]
}
}
}
Included Tools
Planned tools (none implemented yet):
| Tool | Description | Status |
|---|---|---|
search |
Search the web | ⏳ Planned |
fetch |
Fetch and parse web pages | ⏳ Planned |
shell |
Execute shell commands | ⏳ Planned |
read_file |
Read files | ⏳ Planned |
write_file |
Write files | ⏳ Planned |
grep |
Search project contents | ⏳ Planned |
git_status |
Git status | ⏳ Planned |
git_diff |
Git diff | ⏳ Planned |
git_commit |
Create commits | ⏳ Planned |
list_dir |
List directories | ⏳ Planned |
More tools will be added over time.
Philosophy
YAMS follows a few simple rules:
Local-first
Your tools should work on your machine without requiring cloud infrastructure.
Unix-style
Small composable tools beat giant opaque systems.
Predictable over magical
Agents need reliable tooling more than “AI-native” abstractions.
Boring technology wins
Python. JSON. stdio. HTTP.
These things work.
Development
Clone the repository:
git clone https://github.com/your-org/yams.git
cd yams
Install dependencies:
uv sync
Run the server:
uv run yams
Run tests:
uv run pytest
Lint:
uv run ruff check
Format:
uv run ruff format
Project Structure
yams/
├── pyproject.toml
├── src/yams/
│ ├── server.py
│ ├── tools/
│ ├── transport/
│ └── config/
├── tests/
└── README.md
Roadmap
- Browser automation tools
- Better sandboxing
- Remote execution support
- Tool permissions
- Persistent sessions
- Caching
- Authentication support
- Plugin system
Non-Goals
YAMS is not:
- an agent framework
- an orchestration platform
- a workflow engine
- a hosted service
- an IDE replacement
It is just an MCP server.
Name
Yes, the name is recursive.
No, this probably didn't need to exist.
License
MIT
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。