Praison AI

MCP • AI Agent SDK

MCP: Model Context Protocol (MCP) integration for PraisonAI Agents.

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

ParamField Any

No description available.

ParamField Any

No description available.

Methods

list_active_server_names()

Return the set of MCP server names currently registered this run.

 apply_tool_filters()

Public API to (re)apply allow/deny tool filters to this instance.

 with_tool_prefix()

Namespace this server’s tool names with `prefix_` to avoid

 get_tools()

Get the list of tool functions from this MCP instance.

 get_resources()

List resources/resource-templates advertised by the MCP server.

 get_prompts()

List prompt templates advertised by the MCP server.

 to_openai_tool()

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

 shutdown()

Explicitly shut down MCP resources.

Usage

python
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 448

Related Documentation

MCP Concept MCP Lifecycle