## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.
## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.SIGN UP
## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.LOG IN
Connect Autogen to Platerecognizer MCP. Show your alpr usage stats for june, how many plates did we scan this month?, and more using natural language, with authentication handled for you.
Platerecognizer is an ALPR service for detecting and decoding license plates from images and videos. It streamlines automated vehicle identification for security, compliance, and analytics.
This guide walks you through connecting Platerecognizer to AutoGen using the Composio tool router. By the end, you'll have a working Platerecognizer agent that can read license plates and get snapshot statistics through natural language commands.
This guide will help you understand how to give your AutoGen agent real control over a Platerecognizer account through Composio's Platerecognizer MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.
McpWorkbench and StreamableHttpServerParamsAutogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.
Key features include:
The Platerecognizer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Platerecognizer account. It provides structured and secure access to your license plate recognition data, so your agent can monitor usage, retrieve recognition statistics, track monthly activity, and help you stay on top of your ALPR operations.
Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK
The tool router generates a secure MCP URL that your agents can access to perform actions.
The Composio SDK follows a three-phase workflow:
You will need:
OpenAIChatCompletionClient)pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-toolsInstall Composio, Autogen extensions, and dotenv.
What's happening:
composio connects your agent to Platerecognizer via MCPautogen-agentchat provides the AssistantAgent classautogen-ext-openai provides the OpenAI model clientautogen-ext-tools provides MCP workbench supportCOMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.comCreate a .env file in your project folder.
What's happening:
COMPOSIO_API_KEY is required to talk to ComposioOPENAI_API_KEY is used by Autogen's OpenAI clientUSER_ID is how Composio identifies which user's Platerecognizer connections to useimport asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams
load_dotenv()
async def main():
# Initialize Composio and create a Platerecognizer session
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
user_id=os.getenv("USER_ID"),
toolkits=["platerecognizer"]
)
url = session.mcp.urlload_dotenv() reads your .env fileComposio(api_key=...) initializes the SDKcreate(...) creates a Tool Router session that exposes Platerecognizer toolssession.mcp.url is the MCP endpoint that Autogen will connect to# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
url=url,
timeout=30.0,
sse_read_timeout=300.0,
terminate_on_close=True,
headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.
What's happening:
url points to the Tool Router MCP endpoint from Composiotimeout is the HTTP timeout for requestssse_read_timeout controls how long to wait when streaming responsesterminate_on_close=True cleans up the MCP server process when the workbench is closed# Create model client
model_client = OpenAIChatCompletionClient(
model="gpt-5",
api_key=os.getenv("OPENAI_API_KEY")
)
# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
# Create Platerecognizer assistant agent with MCP tools
agent = AssistantAgent(
name="platerecognizer_assistant",
description="An AI assistant that helps with Platerecognizer operations.",
model_client=model_client,
workbench=workbench,
model_client_stream=True,
max_tool_iterations=10
)What's happening:
OpenAIChatCompletionClient wraps the OpenAI model for AutogenMcpWorkbench connects the agent to the MCP toolsAssistantAgent is configured with the Platerecognizer tools from the workbenchprint("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Platerecognizer related question or task to the agent.\n")
# Conversation loop
while True:
user_input = input("You: ").strip()
if user_input.lower() in ["exit", "quit", "bye"]:
print("\nGoodbye!")
break
if not user_input:
continue
print("\nAgent is thinking...\n")
# Run the agent with streaming
try:
response_text = ""
async for message in agent.run_stream(task=user_input):
if hasattr(message, "content") and message.content:
response_text = message.content
# Print the final response
if response_text:
print(f"Agent: {response_text}\n")
else:
print("Agent: I encountered an issue processing your request.\n")
except Exception as e:
print(f"Agent: Sorry, I encountered an error: {str(e)}\n")You:agent.run_stream(...) yields streaming messages as the agent thinks and calls toolsexit, quit, or bye ends the loopHere's the complete code to get you started with Platerecognizer and AutoGen:
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams
load_dotenv()
async def main():
# Initialize Composio and create a Platerecognizer session
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
user_id=os.getenv("USER_ID"),
toolkits=["platerecognizer"]
)
url = session.mcp.url
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
url=url,
timeout=30.0,
sse_read_timeout=300.0,
terminate_on_close=True,
headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)
# Create model client
model_client = OpenAIChatCompletionClient(
model="gpt-5",
api_key=os.getenv("OPENAI_API_KEY")
)
# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
# Create Platerecognizer assistant agent with MCP tools
agent = AssistantAgent(
name="platerecognizer_assistant",
description="An AI assistant that helps with Platerecognizer operations.",
model_client=model_client,
workbench=workbench,
model_client_stream=True,
max_tool_iterations=10
)
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Platerecognizer related question or task to the agent.\n")
# Conversation loop
while True:
user_input = input("You: ").strip()
if user_input.lower() in ['exit', 'quit', 'bye']:
print("\nGoodbye!")
break
if not user_input:
continue
print("\nAgent is thinking...\n")
# Run the agent with streaming
try:
response_text = ""
async for message in agent.run_stream(task=user_input):
if hasattr(message, 'content') and message.content:
response_text = message.content
# Print the final response
if response_text:
print(f"Agent: {response_text}\n")
else:
print("Agent: I encountered an issue processing your request.\n")
except Exception as e:
print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
if __name__ == "__main__":
asyncio.run(main())toolkits list, for example notion or hubspotEvery Platerecognizer action and event your agent gets out of the box.
Use Platerecognizer MCP with Claude Code
Use Platerecognizer MCP with Claude Cowork
Use Platerecognizer MCP with OpenAI Agents SDK
Use Platerecognizer MCP with Claude Agent SDK
Use Platerecognizer MCP with Grok Bot
Use Platerecognizer MCP with Codex
Use Platerecognizer MCP with OpenClaw
Use Platerecognizer MCP with Hermes
Use Platerecognizer MCP with Atomic Agent
Use Platerecognizer MCP with Google ADK
Use Platerecognizer MCP with LangChain
Use Platerecognizer MCP with Vercel AI SDK
Use Platerecognizer MCP with Mastra AI
Use Platerecognizer MCP with LlamaIndex
Use Platerecognizer MCP with CrewAI
Use Platerecognizer MCP with Pydantic AI
Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.
Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.
Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows.
SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.
Managed auth, hosted MCP servers, and every Platerecognizer tool your agent needs.Free to start.
## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.Start building