How to integrate Peopledatalabs MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Peopledatalabs Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Peopledatalabs to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Peopledatalabs agent that can enrich this email with full person profile, standardize and clean this company name, get detailed info for the skill 'python', find people with 'data scientist' in new york through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Peopledatalabs account through Composio's Peopledatalabs 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 necessary dependencies
  • Initialize Composio and create a Tool Router session for Peopledatalabs
  • Configure an AI agent that can use Peopledatalabs as a tool
  • Run a live chat session where you can ask the agent to perform Peopledatalabs operations

What is open-ai-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 Peopledatalabs MCP server, and what's possible with it?

The Peopledatalabs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Peopledatalabs account. It provides structured and secure access to rich B2B data, so your agent can enrich profiles, standardize company details, validate customer information, and perform advanced searches with ease.

  • Comprehensive person data enrichment: Automatically enhance individual profiles using identifiers like email, phone, or full name combined with company or location data.
  • Company data validation and enrichment: Instantly verify and enrich company details with firmographics, employee counts, and standardized fields to power your workflows.
  • Advanced person search and filtering: Leverage Elasticsearch-powered queries to find the exact professional profiles you need using job title, skills, experience, and more.
  • Data cleaning and standardization: Cleanse and structure raw company, school, or location data to maintain high-quality records in your systems.
  • Skill and job title enrichment: Provide context and standardized information for job titles or professional skills to improve analytics and targeting.

Supported Tools & Triggers

Tools
Autocomplete field suggestionsProvides autocompletion suggestions for a specific field (e.
Clean company dataCleans and standardizes company information based on a name, website, or profile url; providing at least one of these inputs is highly recommended for meaningful results.
Clean location dataCleans and standardizes a raw, unformatted location string into a structured representation, provided the input is a recognizable geographical place.
Clean school dataCleans and standardizes school information; provide at least one of the school's name, website, or profile for optimal results.
Person Search with ElasticsearchPerforms a search for person profiles within people data labs using a custom elasticsearch domain specific language (dsl) query.
Enrich Company DataEnriches company data from people data labs with details like firmographics and employee counts, requiring at least one company identifier.
Enrich IP DataEnriches an ip address with company, location, metadata, and person data from people data labs.
Enrich job title dataEnhances a job title by providing additional contextual information and details.
Enrich person dataEnriches person data using various identifiers; requires a primary id (profile, email, phone, email hash, lid, pdl id) or a name (full, or first and last) combined with another demographic detail (e.
Enrich skill dataRetrieves detailed, standardized information for a given skill by querying the people data labs skill enrichment api; for best results, provide a recognized professional skill or area of expertise.
Generate Search QueryConverts natural language queries into structured pdl elasticsearch queries for people or company searches; generates optimized query structure without executing the search.
Get column detailsRetrieves predefined enum values for a column name from `enum mappings.
Get schemaRetrieves the schema, including field names, descriptions, and data types, for 'person' or 'company' entity types.
Identify person dataRetrieves detailed profile information for an individual from people data labs (pdl), requiring at least one identifier such as email, phone, profile url, name, or company.
People Search with ElasticsearchSearches for person profiles in the people data labs (pdl) database using an elasticsearch domain specific language (dsl) query.

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

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Peopledatalabs 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 Peopledatalabs.

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 Peopledatalabs Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["peopledatalabs"]
)

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 peopledatalabs.
  • The router checks the user's Peopledatalabs connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Peopledatalabs.
  • This approach keeps things lightweight and lets the agent request Peopledatalabs 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 Peopledatalabs. "
        "Help users perform Peopledatalabs 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 Peopledatalabs 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 Peopledatalabs 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 Peopledatalabs.
  • 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 Peopledatalabs and open-ai-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=["peopledatalabs"]
)
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 Peopledatalabs. "
        "Help users perform Peopledatalabs 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 Peopledatalabs MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Peopledatalabs.

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 Peopledatalabs MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Peopledatalabs MCP with Claude Agent SDK

Google ADK

Google ADK

Use Peopledatalabs MCP with Google ADK

LangChain

LangChain

Use Peopledatalabs MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Peopledatalabs MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Peopledatalabs MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Peopledatalabs MCP with LlamaIndex

CrewAI

CrewAI

Use Peopledatalabs MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Peopledatalabs 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 Peopledatalabs 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 callā†—Get started for free