Use an Agent as a tool for another agent.¶
Multi-Agent systems are complicated! Enter the A2A protocol by Google: this protocol allows for simpler communication between agents, and easily enables the use of an agent as a tool for another agent. In this tutorial we'll show how you can create a few agents with any-agent and have an agent be provided as a tool for the other agent.
This tutorial assumes basic familiarity with any-agent: if you haven't used any-agent before you may also find the Creating your first agent cookbook to be useful. You also may find the other A2A related cookbook to be useful: Serve an Agent with A2A
Note: because this tutorial relies upon advanced stdio/stderr communication using the MCP Server, it cannot be run on Google Colab.
Install Dependencies¶
any-agent uses the python asyncio module to support async functionality. When running in Jupyter notebooks, this means we need to enable the use of nested event loops. We'll install any-agent and enable this below using nest_asyncio.
In [ ]:
Copied!
%pip install 'any-agent[a2a]'
import nest_asyncio
nest_asyncio.apply()
%pip install 'any-agent[a2a]'
import nest_asyncio
nest_asyncio.apply()
In [2]:
Copied!
import os
from getpass import getpass
# This notebook communicates with Mistral models using the Mistral API.
if "MISTRAL_API_KEY" not in os.environ:
print("MISTRAL_API_KEY not found in environment!")
api_key = getpass("Please enter your MISTRAL_API_KEY: ")
os.environ["MISTRAL_API_KEY"] = api_key
print("MISTRAL_API_KEY set for this session!")
else:
print("MISTRAL_API_KEY found in environment.")
import os
from getpass import getpass
# This notebook communicates with Mistral models using the Mistral API.
if "MISTRAL_API_KEY" not in os.environ:
print("MISTRAL_API_KEY not found in environment!")
api_key = getpass("Please enter your MISTRAL_API_KEY: ")
os.environ["MISTRAL_API_KEY"] = api_key
print("MISTRAL_API_KEY set for this session!")
else:
print("MISTRAL_API_KEY found in environment.")
MISTRAL_API_KEY found in environment.
Configure the first two agents and serve them over A2A¶
Let's give our first two "helper" agents some very simple capabilities. For this demo, we'll use the async method agent.serve_async so that we can easily run all of the agents from inside the notebook in a single python process.
In [ ]:
Copied!
import asyncio
import httpx
from any_agent import AgentConfig, AnyAgent
from any_agent.config import MCPStdio
from any_agent.serving import A2AServingConfig
# This MCP Tool relies upon uvx https://docs.astral.sh/uv/getting-started/installation/
time_tool = MCPStdio(
command="uvx",
args=["mcp-server-time", "--local-timezone=America/New_York"],
tools=[
"get_current_time",
],
)
time = await AnyAgent.create_async(
"tinyagent", # See all options in https://mozilla-ai.github.io/any-agent/
AgentConfig(
model_id="mistral/mistral-small-latest",
name="time_agent",
description="I'm an agent to help with getting the time",
tools=[time_tool],
),
)
time_handle = await time.serve_async(A2AServingConfig(port=0, endpoint="/time"))
weather_expert = await AnyAgent.create_async(
"tinyagent",
AgentConfig(
model_id="mistral/mistral-small-latest",
name="weather_expert",
instructions="You're an expert that is an avid skier, recommend a great location to ski given a time of the year",
description="I'm an agent that is an expert in recommending my favorite location given a time of the year",
),
)
weather_handle = await weather_expert.serve_async(
A2AServingConfig(port=0, endpoint="/location_recommender")
)
weather_port = weather_handle.port
time_port = time_handle.port
max_attempts = 20
poll_interval = 0.5
attempts = 0
time_url = f"http://localhost:{time_port}"
weather_url = f"http://localhost:{weather_port}"
async with httpx.AsyncClient() as client:
while True:
try:
# Try to make a basic GET request to check if server is responding
await client.get(time_url, timeout=1.0)
print(f"Server is ready at {weather_url}")
break
except (httpx.RequestError, httpx.TimeoutException):
# Server not ready yet, continue polling
pass
await asyncio.sleep(poll_interval)
attempts += 1
if attempts >= max_attempts:
msg = f"Could not connect to the servers. Tried {max_attempts} times with {poll_interval} second interval."
raise ConnectionError(msg)
import asyncio
import httpx
from any_agent import AgentConfig, AnyAgent
from any_agent.config import MCPStdio
from any_agent.serving import A2AServingConfig
# This MCP Tool relies upon uvx https://docs.astral.sh/uv/getting-started/installation/
time_tool = MCPStdio(
command="uvx",
args=["mcp-server-time", "--local-timezone=America/New_York"],
tools=[
"get_current_time",
],
)
time = await AnyAgent.create_async(
"tinyagent", # See all options in https://mozilla-ai.github.io/any-agent/
AgentConfig(
model_id="mistral/mistral-small-latest",
name="time_agent",
description="I'm an agent to help with getting the time",
tools=[time_tool],
),
)
time_handle = await time.serve_async(A2AServingConfig(port=0, endpoint="/time"))
weather_expert = await AnyAgent.create_async(
"tinyagent",
AgentConfig(
model_id="mistral/mistral-small-latest",
name="weather_expert",
instructions="You're an expert that is an avid skier, recommend a great location to ski given a time of the year",
description="I'm an agent that is an expert in recommending my favorite location given a time of the year",
),
)
weather_handle = await weather_expert.serve_async(
A2AServingConfig(port=0, endpoint="/location_recommender")
)
weather_port = weather_handle.port
time_port = time_handle.port
max_attempts = 20
poll_interval = 0.5
attempts = 0
time_url = f"http://localhost:{time_port}"
weather_url = f"http://localhost:{weather_port}"
async with httpx.AsyncClient() as client:
while True:
try:
# Try to make a basic GET request to check if server is responding
await client.get(time_url, timeout=1.0)
print(f"Server is ready at {weather_url}")
break
except (httpx.RequestError, httpx.TimeoutException):
# Server not ready yet, continue polling
pass
await asyncio.sleep(poll_interval)
attempts += 1
if attempts >= max_attempts:
msg = f"Could not connect to the servers. Tried {max_attempts} times with {poll_interval} second interval."
raise ConnectionError(msg)
Configure and use the Third Agent¶
Now that the first two agents are serving over A2A, our main agent can be given access to use it just like a tool! In order to do this you use the a2a_tool_async function which retrieves the info about the agent and allows you to call it.
In [4]:
Copied!
from any_agent import AgentConfig, AnyAgent
from any_agent.tools import a2a_tool_async
config = AgentConfig(
model_id="mistral/mistral-small-latest",
instructions="Use the available tools to obtain additional information to answer the query.",
description="The orchestrator that can use other agents via tools using the A2A protocol.",
tools=[
await a2a_tool_async(
f"http://localhost:{time_port}/time",
http_kwargs={
"timeout": 30
}, # This gives the time agent up to 30 seconds to respond to each request
),
await a2a_tool_async(
f"http://localhost:{weather_port}/location_recommender",
http_kwargs={
"timeout": 30
}, # This gives the weather agent up to 30 seconds to respond to each request
),
],
)
agent = await AnyAgent.create_async(
agent_framework="tinyagent",
agent_config=config,
)
agent_trace = await agent.run_async("Where should I go this weekend to ski?")
print(agent_trace.final_output)
from any_agent import AgentConfig, AnyAgent
from any_agent.tools import a2a_tool_async
config = AgentConfig(
model_id="mistral/mistral-small-latest",
instructions="Use the available tools to obtain additional information to answer the query.",
description="The orchestrator that can use other agents via tools using the A2A protocol.",
tools=[
await a2a_tool_async(
f"http://localhost:{time_port}/time",
http_kwargs={
"timeout": 30
}, # This gives the time agent up to 30 seconds to respond to each request
),
await a2a_tool_async(
f"http://localhost:{weather_port}/location_recommender",
http_kwargs={
"timeout": 30
}, # This gives the weather agent up to 30 seconds to respond to each request
),
],
)
agent = await AnyAgent.create_async(
agent_framework="tinyagent",
agent_config=config,
)
agent_trace = await agent.run_async("Where should I go this weekend to ski?")
print(agent_trace.final_output)
╭──────────────────────────────────────────── CALL_LLM: mistral/mistral-medium-latest ─────────────────────────────────────────────╮ │ ╭─ INPUT ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ [ │ │ │ │ { │ │ │ │ "role": "system", │ │ │ │ "content": "Use the available tools to obtain additional information to answer the query." │ │ │ │ }, │ │ │ │ { │ │ │ │ "role": "user", │ │ │ │ "content": "Where should I go this weekend to ski?" │ │ │ │ } │ │ │ │ ] │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ [ │ │ │ │ { │ │ │ │ "tool.name": "call_time_agent", │ │ │ │ "tool.args": "{\"query\": \"current date\"}" │ │ │ │ }, │ │ │ │ { │ │ │ │ "tool.name": "call_weather_expert", │ │ │ │ "tool.args": "{\"query\": \"recommend best location for skiing right now\"}" │ │ │ │ } │ │ │ │ ] │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ USAGE ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "input_tokens": 341, │ │ │ │ "output_tokens": 54 │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────── CALL_LLM: mistral/mistral-small-latest ─────────────────────────────────────────────╮ │ ╭─ INPUT ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ [ │ │ │ │ { │ │ │ │ "role": "system", │ │ │ │ "content": "You are an agent - please keep going until the user's query is completely resolved, before │ │ │ │ }, │ │ │ │ { │ │ │ │ "role": "user", │ │ │ │ "content": "current date" │ │ │ │ } │ │ │ │ ] │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ [ │ │ │ │ { │ │ │ │ "tool.name": "get_current_time", │ │ │ │ "tool.args": "{\"timezone\":\"America/New_York\"}" │ │ │ │ } │ │ │ │ ] │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ USAGE ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "input_tokens": 224, │ │ │ │ "output_tokens": 18 │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────── EXECUTE_TOOL: get_current_time ─────────────────────────────────────────╮ │ ╭─ Input ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "timezone": "America/New_York" │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "timezone": "America/New_York", │ │ │ │ "datetime": "2025-06-27T08:20:15-04:00", │ │ │ │ "is_dst": true │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────── CALL_LLM: mistral/mistral-small-latest ─────────────────────────────────────────────╮ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ The current date is June 27, 2025. │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ USAGE ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "input_tokens": 292, │ │ │ │ "output_tokens": 13 │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭───────────────────────────────────────── EXECUTE_TOOL: call_time_agent ─────────────────────────────────────────╮ │ ╭─ Input ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "query": "current date" │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Status: TaskState.completed │ │ │ │ │ │ │ │ Message: {"result":"The current date is June 27, 2025."} │ │ │ │ │ │ │ │ TaskId: 16f71ba4-4fbe-4905-a528-9b3e26fed354 │ │ │ │ │ │ │ │ Timestamp: 2025-06-27T12:20:16.700991+00:00 │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────── CALL_LLM: mistral/mistral-small-latest ─────────────────────────────────────────────╮ │ ╭─ INPUT ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ [ │ │ │ │ { │ │ │ │ "role": "system", │ │ │ │ "content": "You're an expert that is an avid skier, recommend a great location to ski given a time of t │ │ │ │ }, │ │ │ │ { │ │ │ │ "role": "user", │ │ │ │ "content": "recommend best location for skiing right now" │ │ │ │ } │ │ │ │ ] │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Could you please tell me your current location or where you are planning to travel from? This will help me │ │ │ │ recommend the best skiing destination for you right now. │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ USAGE ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "input_tokens": 52, │ │ │ │ "output_tokens": 32 │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─────────────────────────────────────── EXECUTE_TOOL: call_weather_expert ───────────────────────────────────────╮ │ ╭─ Input ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "query": "recommend best location for skiing right now" │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Status: TaskState.input_required │ │ │ │ │ │ │ │ Message: {"result":"Please specify your current location or where you plan to travel from so I can │ │ │ │ recommend the best skiing destinations for this time of year."} │ │ │ │ │ │ │ │ TaskId: fd36c8a1-7670-4d2c-ac2f-254402eed58a │ │ │ │ │ │ │ │ Timestamp: 2025-06-27T12:20:19.126381+00:00 │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────── CALL_LLM: mistral/mistral-medium-latest ─────────────────────────────────────────────╮ │ ╭─ OUTPUT ────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Today is June 27, 2025. To recommend the best skiing destination for this weekend, could you please tell me │ │ │ │ your current location or the place you plan to travel from? This will help me suggest the most suitable ski │ │ │ │ locations for this time of year. │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ │ ╭─ USAGE ─────────────────────────────────────────────────────────────────────────────────────────────────────╮ │ │ │ { │ │ │ │ "input_tokens": 584, │ │ │ │ "output_tokens": 54 │ │ │ │ } │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
Today is June 27, 2025. To recommend the best skiing destination for this weekend, could you please tell me your current location or the place you plan to travel from? This will help me suggest the most suitable ski locations for this time of year.
Shut down the servers and the agents¶
The following code can be used to gracefully shut down the agents that are serving via A2A.
In [5]:
Copied!
await time_handle.shutdown()
await weather_handle.shutdown()
await time_handle.shutdown()
await weather_handle.shutdown()