How to integrate Algolia MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

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 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.

Also integrate Algolia with

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 A/B test comparing search performance between two index variants.
Add or Replace RecordTool to add or replace a specific record in an index by objectID.
Add Record to IndexTool to add a record to an index with auto-generated objectID.
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.
Clear SynonymsTool to delete all synonyms from 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.
Create API KeyTool to create a new API key with specific permissions and restrictions.
Create AuthenticationTool to create a new authentication resource in Algolia.
Create DestinationTool to create a new destination in Algolia Ingestion API.
Create Ingestion TaskTool to create a new ingestion task connecting a source to a destination in Algolia.
Create or Update Recommend RulesTool to create or update a batch of Recommend Rules in an index.
Create Query Suggestions ConfigTool to create a new Query Suggestions configuration for an Algolia index.
Create SourceTool to create a new data source in Algolia Ingestion API.
Create TransformationTool to create a new transformation in Algolia Ingestion API.
Delete AB TestTool to delete an A/B test by its unique identifier.
Delete API KeyTool to delete an API key.
Delete AuthenticationTool to delete an authentication resource from Algolia.
Delete Query Suggestions ConfigTool to delete a Query Suggestions configuration for the specified index.
Delete DestinationTool to delete a destination in Algolia Ingestion API.
Delete IndexTool to delete the specified index and all its records.
Delete Multiple RecordsTool to delete multiple records from an Algolia index.
Delete Recommend RuleTool to delete a Recommend rule from a recommendation scenario.
Delete Records by FilterTool to delete records matching a filter from an Algolia index.
Delete RuleTool to delete the specified rule from an index.
Delete SourceTool to delete a source from the Algolia Ingestion API.
Delete SynonymTool to delete a synonym from a specified index.
Delete TransformationTool to delete a transformation in Algolia Ingestion API.
Delete User ProfileTool to delete a user profile from personalization.
Delete User TokenTool to delete all events related to a user token from events metrics and analytics.
Batch Operations on Multiple IndicesTool to perform batch operations (add, update, delete) across multiple Algolia indices in a single request.
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 A/B TestTool to retrieve detailed information about an A/B test by its ID.
Get Add to Cart RateTool to retrieve add-to-cart rate metrics for e-commerce search analytics.
Get API KeyTool to retrieve the permissions and details of a specific API key.
Get App Task StatusTool to check the status of an application task.
Get AuthenticationTool to retrieve an authentication resource by its ID.
Get Average Click PositionTool to retrieve average click position metrics from Algolia Analytics.
Get Click PositionsTool to retrieve the distribution of clicks by position from Algolia Analytics.
Get Click Through RateTool to retrieve click-through rate (CTR) for searches with at least one click event.
Get Query Suggestions ConfigTool to retrieve a Query Suggestions configuration by index name.
Get Personalization ConfigTool to retrieve the advanced personalization configuration.
Get Conversion RateTool to retrieve conversion rate for searches with conversion events.
Get DestinationTool to retrieve a destination by its ID.
Get Dictionary LanguagesTool to list available languages for dictionary entries.
Get Dictionary SettingsTool to retrieve dictionary settings for all dictionaries.
Get LogsTool to retrieve log entries for API requests made to your Algolia application.
Get No Click RateTool to retrieve the rate of searches that received no clicks.
Get No Results RateTool to retrieve the fraction of searches that didn't return any results.
Get No Results SearchesTool to retrieve the most frequent searches that produced zero results.
Get Object PositionTool to retrieve an object’s position in a result set.
Get multiple objectsTool to retrieve multiple records from an index.
Get Purchase RateTool to retrieve purchase rate metrics for searches that led to purchase events.
Get Recommend RuleTool to retrieve a Recommend rule that was previously created in the Algolia dashboard.
Get Recommend Task StatusTool to check the status of a Recommend task.
Get Record from IndexTool to retrieve a specific record from an index by its objectID.
Get RevenueTool to retrieve revenue data from Algolia Analytics.
Get RuleTool to retrieve a specific rule by its objectID from an index.
Get Searches CountTool to retrieve the number of searches within a time range, including a daily breakdown.
Get Searches No ClicksTool to retrieve top searches that did not receive any clicks.
Get Index SettingsTool to retrieve the settings of a specified index.
Get SourceTool to retrieve a source from the Algolia Ingestion API.
Get SynonymTool to retrieve a specific synonym by its objectID.
Get Task StatusTool to check the status of an asynchronous task.
Get Top CountriesTool to retrieve top countries by search volume for a specified index.
Get Top Filter AttributesTool to retrieve top filter attributes from Algolia Analytics.
Get Top Filter For AttributeTool to retrieve top filter values for a specific attribute from Algolia Analytics.
Get Top Filters No ResultsTool to retrieve top filters for searches that returned no results from Algolia Analytics.
Get Top HitsTool to retrieve the object IDs of the most frequent search results from Algolia Analytics.
Get Top SearchesTool to retrieve the most popular searches from Algolia Analytics.
Get TransformationTool to retrieve a transformation by its ID from Algolia's Ingestion API.
Get Usage StatisticsTool to retrieve Algolia usage statistics over a specified time period.
Get Usage for IndexTool to retrieve usage statistics for a specific Algolia index over a time period.
Get UsersTool to retrieve a list of user profiles from Algolia advanced personalization.
Get Users CountTool to retrieve the number of unique users within a time range, including daily breakdown.
Index ExistsTool to check if an Algolia index exists.
Init Insights API ClientTool to initialize the Algolia Insights API client.
List AB TestsTool to list all A/B tests configured for this application.
List API KeysTool to list all API keys associated with your Algolia application, including their permissions and restrictions.
List AuthenticationsTool to list authentication resources from Algolia.
List DestinationsTool to list destinations in Algolia.
List IndicesTool to list all indices and their metadata.
List Ingestion TasksTool to retrieve a list of ingestion tasks from Algolia.
List Query Suggestions ConfigurationsTool to retrieve all Query Suggestions configurations for an Algolia application.
List Task RunsTool to list task runs.
List SourcesTool to list sources from the Algolia Ingestion API.
List TransformationsTool to list all transformations in Algolia Ingestion API.
Partial Update ObjectsTool to partially update multiple records in the specified index.
Push Records to TaskTool to push records to an Algolia task by task ID.
Replace All RulesTool to push a new set of rules, erasing previous ones.
Replace TaskTool to fully replace a task in Algolia Ingestion API.
Restore API KeyTool to restore a deleted API key within 72 hours of deletion.
Save RuleTool to create or replace a rule in an index.
Save SynonymTool to add or update a synonym in the specified index.
Save SynonymsTool to batch create or replace synonyms in an Algolia index.
Search AuthenticationsTool to search for authentication resources by IDs in Algolia.
Search DestinationsTool to search for specific destinations by their IDs.
Search Dictionary EntriesTool to search dictionary entries in Algolia dictionaries.
Search Facet ValuesTool to search for values of a specified facet attribute.
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 Recommend RulesTool to search for Recommend rules in the specified index and model.
Search SourcesTool to search for sources by IDs in Algolia Ingestion API.
Search SynonymsTool to search for synonyms in the specified index.
Search TransformationsTool to search for transformations by IDs in Algolia Ingestion API.
Set Dictionary SettingsTool to update dictionary settings for Algolia.
Set Personalization StrategyTool to define personalization strategy that controls how user behavior affects search results.
Set Index SettingsTool to update an Algolia index's settings.
Stop AB TestTool to stop an A/B test by its unique identifier.
Try TransformationTool to try a transformation before creating it in Algolia.
Try Transformation Before UpdateTool to test a transformation before updating it in Algolia Ingestion API.
Update API KeyTool to update the permissions and settings of an existing API key.
Update AuthenticationTool to update an authentication resource in Algolia.
Update Query Suggestions ConfigTool to update an existing Query Suggestions configuration.
Update DestinationTool to update a destination in Algolia Ingestion API.
Update Dictionary EntriesTool to add or delete dictionary entries in Algolia dictionaries.
Update Record PartiallyTool to add or update attributes in a single record.
Update SourceTool to update a source in the Algolia Ingestion API.
Update TaskTool to partially update a task in Algolia Ingestion API.
Update TransformationTool to update an existing transformation in Algolia Ingestion API.
Validate SourceTool to validate a source payload before creating it in Algolia.
Validate Source Before UpdateTool to validate a source update payload in the Algolia Ingestion API.

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

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:

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

    # 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 logo

OpenAI Agents SDK

Use Algolia MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Algolia MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Algolia MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Algolia MCP with Claude Cowork

Codex logo

Codex

Use Algolia MCP with Codex

OpenClaw logo

OpenClaw

Use Algolia MCP with OpenClaw

Hermes logo

Hermes

Use Algolia MCP with Hermes

CLI logo

CLI

Use Algolia MCP with CLI

Google ADK logo

Google ADK

Use Algolia MCP with Google ADK

LangChain logo

LangChain

Use Algolia MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Algolia MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Algolia MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Algolia MCP with LlamaIndex

CrewAI logo

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.

Get started for freeGet a demo↗