Skip to content

Connect the MultitaskAI MCP server to CrewAI

CrewAI builds multi-agent crews in Python. Add MultitaskAI to an agent's mcps as an MCPServerHTTP entry with its URL and your API key.

Endpoint

Text
https://mcp.multitaskai.com

Steps

  1. Create an API key in your MultitaskAI account.
  2. Install MCP support with uv add mcp.
  3. Add the MultitaskAI server below to your agent's mcps, with your key in place of YOUR_API_KEY.
  4. Run your crew with kickoff() and check that the agent calls MultitaskAI tools.
Python
from crewai import Agent
from crewai.mcp import MCPServerHTTP

agent = Agent(
    role="Assistant",
    goal="Get work done with MultitaskAI",
    backstory="You use MultitaskAI tools to help the user.",
    mcps=[
        MCPServerHTTP(
            url="https://mcp.multitaskai.com",
            headers={"Authorization": "Bearer YOUR_API_KEY"},
            streamable=True,
        ),
    ],
)

Authentication

CrewAI sends your MultitaskAI API key in the Authorization header. Create a key in your account and use it in place of YOUR_API_KEY. Keep the key out of files you share or commit.

Text
Authorization: Bearer YOUR_API_KEY

Good to know

  • Install MCP support with uv add mcp first.
  • Set streamable=True so CrewAI uses Streamable HTTP.
  • Keep the key in an environment variable rather than in your code.

Official documentation

The CrewAI MCP documentation covers CrewAI's own settings in detail. See the overview for the endpoint and authentication, and pricing for the daily free requests.