A minimal, lightweight client designed to simplify SDK (e.g., LangChain, Agent SDK) adoption into MCP.
Project description
✨ litemcp
A minimal, lightweight client designed to simplify SDK adoption into MCP.
litemcp enables rapid and intuitive integration of various AI SDKs (e.g., LangChain, Agent SDK) into your MCP projects, emphasizing simplicity, flexibility, and minimal dependencies.
🌟 Key Features
- Simplicity: Streamlined interfaces ensure easy integration.
- Flexibility: Quickly adopt diverse SDKs with minimal effort.
- Lightweight: Designed with minimal dependencies to maximize clarity and performance.
🛠 Installation
Install via pip:
pip install litemcp
🚀 Quick Start
Here's a concise example demonstrating integration with OpenAI Agent SDK:
import asyncio
import sys
from mcp_server import MCPServerManager
from openai_agent_sdk import Agent, Runner
async def main():
async with MCPServerManager(sys.argv[1]) as server_manager:
mcp_server_tools = await server_manager.agent_sdk_tools()
agent = Agent(
name="assistant",
instructions="You are an AI assistant.",
tools=mcp_server_tools,
)
result = await Runner.run(agent, "List all the kubernetes clusters")
print(result.final_output)
if __name__ == "__main__":
asyncio.run(main())
📖 MCP Configuration Schema
Configure your MCP environment with optional server enabling and tool exclusion:
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
},
"youtube": {
"command": "npx",
"args": ["-y", "github:anaisbetts/mcp-youtube"],
"exclude_tools": ["..."]
},
"mcp-server-commands": {
"command": "npx",
"args": ["mcp-server-commands"],
"requires_confirmation": [
"run_command",
"run_script"
],
"enabled": false
},
"multicluster-mcp-server": {
"command": "node",
"args": [".../multicluster-mcp-server/build/index.js"],
"enabled": false
}
}
}
- Use
"enabled": true/falseto activate or deactivate servers. - Use
"exclude_tools"to omit unnecessary tools from the current MCP server.
📖 Documentation
Detailed documentation coming soon!
📢 Contributing
Contributions and suggestions are welcome! Please open an issue or submit a pull request.
📜 License
liteMCP is available under the MIT License.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file litemcp-0.1.0.tar.gz.
File metadata
- Download URL: litemcp-0.1.0.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.1 CPython/3.11.11 Darwin/24.3.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ed4114ffda911926fd0c634ae6368886318130fc04a224c73ffd7ec1f84a7da8
|
|
| MD5 |
d78bb2cf98f35e7c24ee0e2c5445f025
|
|
| BLAKE2b-256 |
bff0a67854ce2aee04c0475f9453adc69d6cc45dd8552fcb0d1de84cda5c6150
|
File details
Details for the file litemcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: litemcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 6.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.1 CPython/3.11.11 Darwin/24.3.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f641e63d8eb35f146433e67bda77d707cf3a37b027bae78191a57cabdf83e159
|
|
| MD5 |
634d2e59c1a0b8d666196f05744f557a
|
|
| BLAKE2b-256 |
b10c69967cc8d8d724545770a10dfa053f981c7bd60b18070f591105a5a9683f
|