How to integrate Recallai MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Recallai logo
OpenAI Agents SDK logo
divider

Introduction

This guide walks you through connecting Recallai to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Recallai agent that can start recording your zoom meeting now, list all bots active in meetings, retrieve chat messages from today's calls through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Recallai account through Composio's Recallai MCP server.

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

Also integrate Recallai with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Recallai
  • Configure an AI agent that can use Recallai as a tool
  • Run a live chat session where you can ask the agent to perform Recallai operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Recallai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Recallai account. It provides structured and secure access to your meeting bots and conversation data, so your agent can create bots, manage recordings, retrieve chat messages, and orchestrate meeting participation on your behalf.

  • Automated bot creation and management: Quickly spin up new meeting bots, retrieve details, and remove bots as needed for your meetings.
  • Meeting recording control: Let your agent start or stop recordings during live calls, ensuring you capture the most important moments hands-free.
  • Chat message retrieval: Effortlessly access and analyze chat messages exchanged during meetings, enabling summaries or follow-up actions.
  • Bot participation orchestration: Seamlessly remove bots from calls when their job is done, keeping your meetings efficient and secure.
  • Comprehensive bot listing and oversight: View and manage all active bots connected to your Recallai account for smooth operations and tracking.

Supported Tools & Triggers

Tools
Create botCreate a new bot to join and record a meeting.
Create Calendar IntegrationTool to create a new calendar integration with Google Calendar or Microsoft Outlook.
Create Calendar Authentication TokenTool to generate an authentication token for calendar APIs, scoped to the user.
Create Google LoginTool to create a new Google Login credential within a login group.
Create Google Login GroupTool to create a new Google Login Group for managing bot authentication.
Create Meeting Direct ConnectTool to create a Meeting Direct Connect for Google Meet or Zoom.
Create SDK UploadCreate a new Desktop SDK upload.
Create Zoom OAuth AppTool to create a new Zoom OAuth App integration with Recall.
Delete botDelete a scheduled bot by ID.
Delete Bot MediaDeletes bot media stored by Recall AI.
Delete calendarDelete a calendar by ID.
Delete Calendar UserDelete calendar user and disconnect any connected calendars.
Destroy Google LoginTool to delete an existing Google Login by ID.
Destroy Google Login GroupTool to delete an existing Google Login Group by ID.
Destroy Zoom OAuth AppTool to delete a Zoom OAuth App by ID.
Disconnect Calendar UserTool to disconnect a calendar platform (Google or Microsoft) from the user's Recall.
List audio mixedList audio mixed artifacts from Recall.
List Audio SeparateList audio separation artifacts from recordings.
List botsList all bots in your Recall.
List Bot ScreenshotsList all screenshots captured by a bot during a meeting.
List Calendar EventsGet a list of calendar events from connected calendars.
List calendar meetingsList all calendar meetings for the authenticated calendar user.
List calendarsTool to retrieve a list of calendars integrated with Recall.
List calendar usersList all calendar users created for the account.
List chat messagesGet list of chat messages read by the bot in the meeting(excluding messages sent by the bot itself).
List Google Login GroupsTool to retrieve a list of all Google Login Groups in your Recall.
List Google LoginsTool to retrieve a list of all Google Logins in your Recall.
List Meeting Direct ConnectsList all Meeting Direct Connect instances in your Recall.
List Meeting MetadataList meeting metadata from Recall.
List participant eventsList participant events artifacts from recorded meetings.
List Realtime EndpointsTool to list realtime endpoints from Recall.
List RecordingsTool to list recordings from Recall.
List Desktop SDK UploadsTool to get a paginated list of all Desktop SDK uploads in your Recall.
List Slack TeamsTool to list all Slack team integrations.
List transcriptTool to list transcripts from Recall.
List Video Mixed ArtifactsList video mixed artifacts from recorded meetings.
List video separateList video separate artifacts from Recall.
List zoom meetings to credentialsTool to retrieve mappings from Zoom Meeting IDs to Zoom OAuth Credentials.
List Zoom OAuth App LogsTool to retrieve Zoom OAuth app logs from Recall.
List Zoom OAuth AppsTool to retrieve a list of Zoom OAuth apps configured in Recall.
List Zoom OAuth Credential LogsTool to retrieve all Zoom OAuth Credential logs from Recall.
List Zoom OAuth CredentialsTool to retrieve a list of all Zoom OAuth credentials in your Recall.
Remove bot from callRemoves the bot from the meeting call.
Retrieve Billing UsageRetrieve bot usage statistics for billing purposes.
Retrieve botRetrieve detailed information about a specific bot instance by its ID.
Retrieve calendarsRetrieve detailed information about a specific calendar by its UUID.
Retrieve Google Login GroupTool to retrieve an existing Google Login Group by its ID.
Retrieve Meeting Direct ConnectTool to retrieve detailed information about a Meeting Direct Connect instance by its ID.
Retrieve recordingTool to retrieve detailed information about a specific recording by its UUID.
Retrieve sdk uploadRetrieve detailed information about a Desktop SDK upload instance by its ID.
Retrieve Video MixedRetrieve a video mixed artifact by its ID.
Retrieve Zoom OAuth AppRetrieve detailed information about a specific Zoom OAuth app by its ID.
Start recordingInstructs the bot to start recording the meeting.
Stop recordingStops the current recording for the specified bot.
Update BotTool to partially update a scheduled bot.
Update CalendarUpdate an existing calendar integration in Recall.
Update Calendar UserUpdate recording preferences and calendar connections for a calendar user.
Update Google LoginTool to update an existing Google Login credential.
Update Google Login GroupTool to update an existing Google Login Group in Recall.
Partial Update Google Login GroupTool to partially update an existing Google Login Group in Recall.
Update RecordingTool to update a recording's metadata.
Update Video MixedTool to partially update a video mixed artifact by ID.
Update Zoom OAuth AppTool to update an existing Zoom OAuth App's credentials.

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

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Recallai project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Recallai.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Recallai Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["recallai"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only recallai.
  • The router checks the user's Recallai connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Recallai.
  • This approach keeps things lightweight and lets the agent request Recallai tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Recallai. "
        "Help users perform Recallai operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Recallai and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Recallai operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Recallai.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Recallai and OpenAI Agents SDK:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["recallai"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Recallai. "
        "Help users perform Recallai operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Recallai MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Recallai.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Recallai MCP Agent with another framework

FAQ

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

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

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Recallai tools.

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

Yes, absolutely. You can configure which Recallai 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 Recallai 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.