A standardized way for AI models to connect with tools, data sources, and external systems. One protocol, endless integrations.
Your AI Application
JSON-RPC 2.0
Tools & Data Sources
One unified protocol for all integrations instead of custom implementations
Fine-grained permissions and sandboxed execution for safe tool use
Local processes, remote servers, or cloud-hosted services
Tools, resources, prompts, and sampling for complete control
Bidirectional communication for streaming and live updates
Chain multiple servers together for complex workflows
Create an MCP server that exposes tools to AI models:
from mcp.server import Server, McpError
from mcp.types import Tool, TextContent
server = Server("weather-server")
# Define a tool
@server.tool()
async def get_weather(city: str) -> str:
"""Get current weather for a city."""
# Your implementation here
return f"Weather in {city}: 72°F, Sunny"
# Run the server
if __name__ == "__main__":
import asyncio
asyncio.run(server.run())
import { Client } from "@modelcontextprotocol/sdk";
const client = new Client({
name: "my-app",
version: "1.0.0"
});
// Connect to server
await client.connect(transport);
// List available tools
const tools = await client.listTools();
// Call a tool
const result = await client.callTool({
name: "get_weather",
arguments: { city: "San Francisco" }
});
Read, write, and manage local files
Query and modify database tables
Repositories, issues, and PRs
Send messages and read channels
Web search capabilities
Pages, databases, and blocks
Files, docs, and sheets
SDKs for Python, TypeScript, more
MCP is an open protocol, not proprietary to MythicDot. We're active contributors and believe standardization benefits everyone. Learn more at modelcontextprotocol.io
Connect your AI applications to any data source.
Get Started →