Skip to main content

​
MCP

Defined in the MCP module.
AI Agent Model Context Protocol (MCP) integration for PraisonAI Agents. This class provides a simple way to connect to MCP servers and use their tools within PraisonAI agents.

​
Constructor

​
command_or_string
Any
No description available.
​
args
Any
No description available.

​
Methods

get_tools()

Get the list of tool functions from this MCP instance.

to_openai_tool()

Convert the MCP tool to an OpenAI-compatible tool definition.

shutdown()

Explicitly shut down MCP resources.

​
Usage

from praisonaiagents import Agent
    from praisonaiagents.mcp import MCP
    
    # Method 1: Using command and args separately
    agent = Agent(
        instructions="You are a helpful assistant...",
        llm="gpt-4o-mini",
        tools=MCP(
            command="/path/to/python",
            args=["/path/to/app.py"]
        )
    )
    
    # Method 2: Using a single command string
    agent = Agent(
        instructions="You are a helpful assistant...",
        llm="gpt-4o-mini",
        tools=MCP("/path/to/python /path/to/app.py")
    )
    
    # Method 3: Using an SSE endpoint
    agent = Agent(
        instructions="You are a helpful assistant...",
        llm="gpt-4o-mini",
        tools=MCP("http://localhost:8080/sse")
    )
    
    agent.start("What is the stock price of Tesla?")

​
Source

View on GitHub

praisonaiagents/mcp/mcp.py at line 150

MCP Concept

MCP Lifecycle