SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Token metrics MCP with Autogen

Connect Autogen to Token metrics MCP. Show real-time price for ethereum, list top 10 tokens by market cap, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Token metrics logoToken metrics
Api Key

Token Metrics provides real-time, AI-powered cryptocurrency data and insights via API. Instantly access up-to-date market analytics to supercharge your crypto dashboards and trading bots.

5 Tools

Introduction

This guide walks you through connecting Token metrics to AutoGen using the Composio tool router. By the end, you'll have a working Token metrics agent that can fetch crypto prices, list tokens, check top tokens by market cap, get trading signals, and review technical indicators through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Token metrics account through Composio's Token metrics MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Token metrics with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Token metrics
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Token metrics tools
  • Run a live chat loop where you ask the agent to perform Token metrics operations

What is AutoGen?

Autogen 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:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Token metrics MCP server, and what's possible with it?

The Token metrics MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Token Metrics account. It provides structured and secure access to real-time cryptocurrency data and analytics, so your agent can retrieve token prices, analyze market trends, surface technical indicators, and provide actionable trading signals on your behalf.

  • Real-time price and market data: Instantly get up-to-date prices, trading volumes, and market caps for any supported cryptocurrency, enabling smart portfolio management and trading decisions.
  • Comprehensive token listings: Fetch a paginated list of supported crypto tokens, including metadata like price, supply, and contract details, to stay on top of the ever-evolving market.
  • On-demand technical analysis: Retrieve technical indicators for any token and interval, so your agent can offer in-depth charting and analysis to guide investment strategies.
  • Automated trading signals: Access AI-powered crypto trading entry and exit signals, helping automate or optimize your trading strategies based on actionable insights.
  • Market cap leaderboards: Easily surface the top cryptocurrencies by market capitalization to monitor market trends, discover new opportunities, or rebalance your holdings.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

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.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Token metrics account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Token metrics via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Token metrics connections to use
5

Import dependencies and create Tool Router session

python
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 Token metrics session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["token_metrics"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Token metrics tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# 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 Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# 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 Token metrics assistant agent with MCP tools
    agent = AssistantAgent(
        name="token_metrics_assistant",
        description="An AI assistant that helps with Token metrics operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Token metrics tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Token metrics 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")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Token metrics tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Token metrics and AutoGen:

python
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 Token metrics session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["token_metrics"]
    )
    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 Token metrics assistant agent with MCP tools
        agent = AssistantAgent(
            name="token_metrics_assistant",
            description="An AI assistant that helps with Token metrics 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 Token metrics 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())

Conclusion

You now have an Autogen assistant wired into Token metrics through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Token metrics, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Token metrics action and event your agent gets out of the box.

Get Price

Retrieve price and market metrics for a cryptocurrency by token ID, including price, volume, and market cap.

Get Technical Indicators

Tool to retrieve technical indicators for a token.

Get Tokens

Retrieve a paginated list of supported tokens with price, market cap, supply and contract metadata.

Get Top Market Cap Tokens

Tool to retrieve a list of tokens ranked by market capitalization.

Get Trading Signals

Tool to retrieve entry and exit crypto trading signals.

FRAMEWORKS

How to build Token metrics MCP Agent with another framework

Claude Code logo

Claude Code

Use Token metrics MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Token metrics MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Token metrics MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Token metrics MCP with Claude Agent SDK

Codex logo

Codex

Use Token metrics MCP with Codex

OpenClaw logo

OpenClaw

Use Token metrics MCP with OpenClaw

Hermes logo

Hermes

Use Token metrics MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Token metrics MCP with Atomic Agent

Google ADK logo

Google ADK

Use Token metrics MCP with Google ADK

LangChain logo

LangChain

Use Token metrics MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Token metrics MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Token metrics MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Token metrics MCP with LlamaIndex

CrewAI logo

CrewAI

Use Token metrics MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Token metrics MCP with Pydantic AI

FAQ

Frequently asked questions

With a standalone Token metrics MCP server, the agents and LLMs can only access a fixed set of Token metrics tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Token metrics and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Token metrics tools.

Yes, absolutely. You can configure which Token metrics scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Token metrics data and credentials are handled as safely as possible.

Start with Token metrics.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Token metrics tool your agent needs.Free to start.

Start building