Skip to content
any-agent

Serving

any-agent provides a simple way of serving agents from any of the supported frameworks using different protocols:

Configuring and Serving Agents

Section titled “Configuring and Serving Agents”

You can configure and serve an agent using the A2AServingConfig or MCPServingConfig and the AnyAgent.serve_async method.

For illustrative purposes, we are going to define 2 separate scripts, each defining an agent to answer questions about a specific agent framework (either Google ADK or OpenAI Agents SDK):

google_expert.py
import argparse
import asyncio


from any_agent import AgentConfig, AnyAgent
from any_agent.tools import search_web




async def serve_agent(protocol):
    agent = await AnyAgent.create_async(
        "google",
        AgentConfig(
            name="google_expert",
            model_id="mistral:mistral-small-latest",
            instructions="You can answer questions about the Google Agents Development Kit (ADK) but nothing else",
            description="An agent that can answer questions specifically and only about the Google Agents Development Kit (ADK).",
            tools=[search_web]
        )
    )


    if protocol == "a2a":
        from any_agent.serving import A2AServingConfig
        serving_config = A2AServingConfig(port=5001, endpoint="/google")
    elif protocol == "mcp":
        from any_agent.serving import MCPServingConfig
        serving_config = MCPServingConfig(port=5001, endpoint="/google")


    server_handle = await agent.serve_async(serving_config)
    await server_handle.task


if __name__ == "__main__":
    parser=argparse.ArgumentParser()
    parser.add_argument("protocol", choices=["a2a", "mcp"])
    args = parser.parse_args()
    asyncio.run(serve_agent(args.protocol))

We can now run each of the scripts in a separate terminal and leave them running in the background:

Terminal window
python google_expert.py mcp  ## or a2a
Terminal window
python openai_expert.py a2a  ## or mcp

Using the served agents

Section titled “Using the served agents”

Once the agents are being served using the chosen protocol, you can directly use them using the official clients of each protocol:

Alternatively, as described in Using Agents-As-Tools, we can run another python script containing the main agent that can use the served agents:

import asyncio


from any_agent import AgentConfig, AnyAgent
from any_agent.config import MCPSse
from any_agent.tools import a2a_tool_async




async def main():
    prompt = "What do you know about the Google ADK?"


    google_expert = MCPSse(
        url="http://localhost:5001/google/sse", client_session_timeout_seconds=300)
    openai_expert = await a2a_tool_async(
        url="http://localhost:5002/openai")


    main_agent = await AnyAgent.create_async(
        "tinyagent",
        AgentConfig(
            model_id="gemini/gemini-2.5-pro",
            instructions="You must use the available tools to answer.",
            tools=[google_expert, openai_expert],
        )
    )


    await main_agent.run_async(prompt)


if __name__ == "__main__":
    asyncio.run(main())

More Examples

Section titled “More Examples”

Check out our cookbook example for building and serving an agent via A2A: