How to integrate Algolia MCP with Autogen

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

Introduction

This guide walks you through connecting Algolia to AutoGen using the Composio tool router. By the end, you'll have a working Algolia agent that can export all records from products index, clear all objects from blog_posts index, copy index settings from staging to production, create an ab test comparing two search configs through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Algolia account through Composio's Algolia 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 Algolia
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Algolia tools
  • Run a live chat loop where you ask the agent to perform Algolia 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 Algolia MCP server, and what's possible with it?

The Algolia MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Algolia account. It provides structured and secure access to your search indices, so your agent can perform actions like browsing records, managing index settings, running A/B tests, copying configurations, and tracking search events on your behalf.

  • Comprehensive index browsing and export: Easily direct your agent to retrieve and iterate through all records in any Algolia index for analysis, backup, or migration tasks.
  • Automated A/B test management: Set up, launch, and monitor A/B tests to compare search performance between different index variants or configurations—all without manual coding.
  • Index and rule duplication: Quickly copy entire indices, settings, or query rules from one index to another, streamlining your search deployment and versioning workflows.
  • Bulk index cleanup and resets: Instruct your agent to clear all objects or rules in an index while keeping configurations intact, letting you efficiently manage large data updates or reindexing processes.
  • Real-time event tracking: Capture user interactions like clicks and conversions, enabling your agent to report search analytics and optimize relevance based on actual user behavior.

Supported Tools & Triggers

Tools
Add AB TestTool to create an ab test comparing search performance between two variants.
Browse Algolia IndexTool to retrieve all records from an index.
Clear ObjectsTool to clear records of an index without affecting settings.
Clear RulesTool to delete all rules in an index.
Clicked Object IDsTool to send a click event to algolia to capture clicked items.
Clicked Object IDs After SearchTool to send a click event after a search response.
Converted Object IDsTool to send a conversion event for items outside of search context.
Copy IndexTool to copy the specified index to a new index.
Copy RulesTool to copy rules from one index to another.
Copy Index SettingsTool to copy the settings from one index to another.
Delete IndexTool to delete the specified index and all its records.
Delete Multiple RecordsTool to delete multiple records from an algolia index.
Delete RuleTool to delete the specified rule from an index.
Delete SynonymTool to delete a synonym from a specified index.
Export RulesTool to export all rules defined on an index.
Find ObjectTool to find the first object matching a query or filter in an index.
Get Object PositionTool to retrieve an object’s position in a result set.
Get multiple objectsTool to retrieve multiple records from an index.
Get Index SettingsTool to retrieve the settings of a specified index.
Index ExistsTool to check if an algolia index exists.
Init Insights API ClientTool to initialize the algolia insights api client.
List IndicesTool to list all indices and their metadata.
Partial Update ObjectsTool to partially update multiple records in the specified index.
Replace All RulesTool to push a new set of rules, erasing previous ones.
Save SynonymTool to add or update a synonym in the specified index.
Search Algolia IndexTool to perform a search on a specified algolia index.
Search Multiple IndicesTool to perform searches across multiple indices in a single call.
Search RulesTool to search for rules in the specified index.
Search SynonymsTool to search for synonyms in the specified index.
Set Index SettingsTool to update an algolia index's settings.

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 Algolia 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 Algolia 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 Algolia 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 Algolia session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["algolia"]
    )
    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 Algolia 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 Algolia assistant agent with MCP tools
    agent = AssistantAgent(
        name="algolia_assistant",
        description="An AI assistant that helps with Algolia 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 Algolia 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 Algolia 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 Algolia 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 Algolia 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 Algolia session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["algolia"]
    )
    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 Algolia assistant agent with MCP tools
        agent = AssistantAgent(
            name="algolia_assistant",
            description="An AI assistant that helps with Algolia 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 Algolia 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 Algolia 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 Algolia, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Algolia MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Algolia MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Algolia MCP with Claude Agent SDK

Google ADK

Google ADK

Use Algolia MCP with Google ADK

LangChain

LangChain

Use Algolia MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Algolia MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Algolia MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Algolia MCP with LlamaIndex

CrewAI

CrewAI

Use Algolia MCP with CrewAI

FAQ

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

With a standalone Algolia MCP server, the agents and LLMs can only access a fixed set of Algolia tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Algolia 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 Algolia tools.

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

Yes, absolutely. You can configure which Algolia 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 Algolia data and credentials are handled as safely as possible.

Used by agents from

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