How to integrate Spoki MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Spoki Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Spoki to AutoGen using the Composio tool router. By the end, you'll have a working Spoki agent that can list all whatsapp campaigns scheduled this week, get current report for my spoki account, update contact details for customer mario rossi, list available whatsapp message templates through natural language commands.

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

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

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 Spoki
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Spoki tools
  • Run a live chat loop where you ask the agent to perform Spoki 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 Spoki MCP server, and what's possible with it?

The Spoki MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Spoki account. It provides structured and secure access to your WhatsApp communication workflows, so your agent can manage contacts, send and organize campaigns, retrieve reports, and automate marketing or support tasks with ease.

  • Contact management and automation: Instantly create, update, or delete WhatsApp contacts, and enrich them with custom fields for personalized messaging and streamlined communication.
  • Campaign and automation insights: Let your agent list, search, and filter campaigns or automations, enabling real-time oversight and optimization of your marketing or support workflows.
  • Template and tag organization: Effortlessly retrieve, search, and manage WhatsApp message templates and tags, so your agent can keep communication assets organized and ready to use.
  • Account reporting and analytics: Obtain current reports on message and conversation metrics, giving your agent the power to monitor campaign performance and engagement at a glance.
  • Agency and team coordination: Fetch all accessible agencies for the authenticated account, supporting seamless collaboration across teams or business units from within your AI workflows.

Supported Tools & Triggers

Tools
Create custom fieldTool to create a new custom field.
Create or Update ContactTool to create or update a contact.
Delete contactTool to delete a specific contact.
Get Account Current ReportTool to get the current report for a specified account.
List AgenciesTool to list all agencies accessible to the user.
List AutomationsTool to list, search, and filter automations.
List campaignsTool to list, search, and filter campaigns.
List ContactsTool to list, search, and filter contacts.
List tagsTool to list, search, and filter tags.
List templatesTool to list, search, and filter whatsapp templates.
List TicketsTool to list, search, and filter tickets.
Retrieve AccountTool to retrieve details of a specific account.
Retrieve AutomationTool to retrieve details of a specific automation.
Retrieve ContactTool to retrieve details of a specific contact.
Retrieve TagTool to retrieve details of a specific tag.
Retrieve TemplateTool to retrieve details of a specific template.
List Custom FieldsTool to list, search, and filter custom fields.
Spoki list partnersDeprecated placeholder for spoki list partners action file
List TagsTool to list, search, and filter tags.
List WhatsApp templatesTool to list, search, and filter whatsapp templates.
Retrieve Custom FieldTool to retrieve details of a specific custom field.
Update Custom FieldTool to update a specific custom field.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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

Prerequisites

You will need:

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

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.

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 Spoki via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Spoki connections to use

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 Spoki session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["spoki"]
    )
    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 Spoki tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Spoki assistant agent with MCP tools
    agent = AssistantAgent(
        name="spoki_assistant",
        description="An AI assistant that helps with Spoki 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 Spoki tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Spoki 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 Spoki 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 Spoki 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 Spoki session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["spoki"]
    )
    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 Spoki assistant agent with MCP tools
        agent = AssistantAgent(
            name="spoki_assistant",
            description="An AI assistant that helps with Spoki 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 Spoki 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 Spoki 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 Spoki, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Spoki MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Spoki MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Spoki MCP with Claude Agent SDK

Google ADK

Google ADK

Use Spoki MCP with Google ADK

LangChain

LangChain

Use Spoki MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Spoki MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Spoki MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Spoki MCP with LlamaIndex

CrewAI

CrewAI

Use Spoki MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Spoki MCP?

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

Can I use Tool Router MCP with Autogen?

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 Spoki tools.

Can I manage the permissions and scopes for Spoki while using Tool Router?

Yes, absolutely. You can configure which Spoki 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.

How safe is my data with Composio Tool Router?

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 Spoki data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free