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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.