SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Peopledatalabs MCP with Autogen

Connect Autogen to Peopledatalabs MCP. Enrich this email with full person profile, standardize and clean this company name, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Peopledatalabs logoPeopledatalabs
Api Key

Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data.

26 Tools

Introduction

This guide walks you through connecting Peopledatalabs to AutoGen using the Composio tool router. By the end, you'll have a working Peopledatalabs agent that can enrich person and company data, search people and companies, clean location and school data, and search job postings through natural language commands.

This guide will help you understand how to give your AutoGen 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.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Peopledatalabs with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

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

The People Data Labs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your People Data Labs account. It provides structured and secure access to company records, job postings, data cleaning tools, and dataset schemas, so your agent can search companies, find job postings, standardize company and location data, suggest field values, and inspect available data fields on your behalf.

  • Company record search: Have your agent find companies that match specific criteria using flexible business data queries.
  • Company data cleanup: Let the agent standardize company details from a business name, website, or profile URL.
  • Location standardization: Direct your agent to turn raw location text into clean, structured geographic information.
  • Job posting discovery: Instruct your agent to search People Data Labs job postings using criteria relevant to your recruiting or market research.
  • Schema and field guidance: Have your agent inspect person or company data fields, review allowed values, and suggest completions for partial company, skill, or title text.

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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Peopledatalabs account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

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

4

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 Peopledatalabs connections to use
5

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 Peopledatalabs session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["peopledatalabs"]
    )
    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 Peopledatalabs tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

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
7

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 Peopledatalabs assistant agent with MCP tools
    agent = AssistantAgent(
        name="peopledatalabs_assistant",
        description="An AI assistant that helps with Peopledatalabs 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 Peopledatalabs tools from the workbench
8

Run the interactive chat loop

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

Supported Tools

Every Peopledatalabs action and event your agent gets out of the box.

Bulk Retrieve Persons

Retrieve up to 100 People Data Labs person records by persistent ID.

Clean company data

Cleans 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 company data (POST)

Tool to clean and standardize company data using POST method.

Clean location data

Cleans and standardizes a raw, unformatted location string into a structured representation, provided the input is a recognizable geographical place.

Clean location data (POST)

Tool to clean and standardize location data using POST method.

Clean school data

Cleans and standardizes school information; provide at least one of the school's name, website, or profile for optimal results.

Clean school data (POST)

Tool to clean and standardize school data using POST method.

Enrich Bulk Company Data

Tool to enrich up to 100 companies in a single request using the Bulk Company Enrichment API.

Enrich bulk person data

Enrich up to 100 person profiles in one Bulk Person Enrichment request using supported identifiers and matching parameters.

Enrich Company Data

Enrich company data from People Data Labs with firmographics and employee counts using a company ID, name, social profile, ticker, or website.

Enrich IP Data

Enrich an IP address with People Data Labs company data and, where available and requested, IP location, metadata, and person data.

Enrich job title data

Enrich a job title with a cleaned title, similar titles, and relevant skills.

Enrich person data

Enriches 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 data

Retrieves 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.

Autocomplete field suggestions

Provides autocompletion suggestions for a specific field (e.

Get autocomplete suggestions (POST)

Tool to get autocompletion suggestions using POST method for complex query parameters.

Get column details

Look up predefined enum values and their descriptions for a specified column.

Get schema

Retrieves the schema, including field names, descriptions, and data types, for 'person' or 'company' entity types.

Get subject requests

Retrieve a redirect URL for the authenticated account's person data subject requests, for privacy compliance review.

Identify person data

Identify person profiles in People Data Labs using attributes such as email, phone, profile URL, name, company, or location.

People Search with Elasticsearch

Search People Data Labs person profiles using an Elasticsearch DSL query, with criteria such as job title, skills, company, and location.

Query person changelog

Query the person changelog between dataset versions for updates, additions, deletions, merges, and opt-outs.

Retrieve person

Retrieve one person deterministically by persistent People Data Labs ID.

Company Search with Elasticsearch

Performs a search for company profiles within People Data Labs using a custom Elasticsearch Domain Specific Language (DSL) query.

Search Company Records (POST)

Tool to search and filter company records from the full Company Dataset using Elasticsearch or SQL queries via POST method.

Search job postings

Search PDL's Job Posting Dataset using one filter mode and cursor pagination.

FRAMEWORKS

How to build Peopledatalabs MCP Agent with another framework

Claude Code logo

Claude Code

Use Peopledatalabs MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Peopledatalabs MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Peopledatalabs MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Peopledatalabs MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Peopledatalabs MCP with Grok Bot

Muse logo

Muse

Use Peopledatalabs MCP with Muse

Codex logo

Codex

Use Peopledatalabs MCP with Codex

OpenClaw logo

OpenClaw

Use Peopledatalabs MCP with OpenClaw

Hermes logo

Hermes

Use Peopledatalabs MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Peopledatalabs MCP with Atomic Agent

Google ADK logo

Google ADK

Use Peopledatalabs MCP with Google ADK

LangChain logo

LangChain

Use Peopledatalabs MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Peopledatalabs MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Peopledatalabs MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Peopledatalabs MCP with LlamaIndex

CrewAI logo

CrewAI

Use Peopledatalabs MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Peopledatalabs MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Peopledatalabs.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Peopledatalabs tool your agent needs.Free to start.

Start building