SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Pipeline crm MCP with Pydantic AI

Connect Pydantic AI to Pipeline crm MCP. List all leads added this week, get details for deal with id 789, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Pipeline crm logoPipeline crm
Api Key

Pipeline CRM is a sales-focused customer relationship management platform for teams. It helps track leads, manage deals, and streamline sales workflows for better productivity.

15 Tools

Introduction

This guide walks you through connecting Pipeline crm to Pydantic AI using the Composio tool router. By the end, you'll have a working Pipeline crm agent that can create and update companies, manage deals, list leads and deal stages, and track calendar tasks through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Pipeline crm account through Composio's Pipeline crm MCP server.

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

Also integrate Pipeline crm with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Pipeline crm
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Pipeline crm workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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

The Pipeline crm MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Pipeline crm account. It provides structured and secure access to your sales pipeline data, so your agent can perform actions like tracking leads, managing deals, updating company information, organizing tasks, and streamlining sales workflows on your behalf.

  • Lead and company management: Effortlessly list, retrieve, or delete companies and leads, making it easy to keep your CRM up to date and focused on the right opportunities.
  • Deal tracking and stage management: Let your agent fetch deal details, monitor deal stages, or remove outdated deals to ensure your pipeline always reflects current sales activity.
  • Calendar task organization: Automatically list and retrieve calendar tasks, or pull specific task details by ID to stay on top of follow-ups and scheduled activities.
  • Comprehensive sales workflow automation: Ask your agent to enumerate deal stages, manage associated tasks, and streamline repetitive CRM operations so your team can focus on closing more deals.

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 step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Pipeline crm
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Pipeline crm
  • MCPServerStreamableHTTP connects to the Pipeline crm MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Pipeline crm
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["pipeline_crm"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Pipeline crm tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
pipeline_crm_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[pipeline_crm_mcp],
    instructions=(
        "You are a Pipeline crm assistant. Use Pipeline crm tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Pipeline crm endpoint
  • The agent uses GPT-5 to interpret user commands and perform Pipeline crm operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Pipeline crm.\n")

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", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Pipeline crm API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Pipeline crm and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Pipeline crm
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["pipeline_crm"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    pipeline_crm_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[pipeline_crm_mcp],
        instructions=(
            "You are a Pipeline crm assistant. Use Pipeline crm tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Pipeline crm.\n")

    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", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Pipeline crm through Composio's Tool Router. With this setup, your agent can perform real Pipeline crm actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Pipeline crm for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

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

Create Pipeline CRM Company

Creates a new company record in Pipeline CRM with contact details, address, and social media information.

Create Deal

Tool to create a new deal in Pipeline CRM.

Delete Company

Tool to delete a company by ID in Pipeline CRM.

Delete Deal

Tool to delete a deal by ID.

Delete calendar task

Deletes a Pipeline CRM calendar entry by ID, including a task or event.

Get Company by ID

Retrieves details for a company by ID in Pipeline CRM, including available contact, address, owner, financial, custom field, tag, and next-entry information.

Get Deal by ID

Tool to retrieve details for a specific deal by ID in Pipeline CRM.

Get Deal Stage by ID

Tool to retrieve details for a specific stage by ID in Pipeline CRM.

Get calendar task by ID

Retrieves a calendar entry by ID in Pipeline CRM, including a task or event.

List Companies

List companies in Pipeline CRM with optional filtering, sorting, and pagination.

List Leads

Lists people in Pipeline CRM, returned as leads, with optional creation and update date filters and pagination.

List Deal Stages

Tool to list deal stages.

List calendar tasks

Tool to list calendar tasks.

List Users

List users in Pipeline CRM account with optional pagination.

Update Company

Tool to update an existing company by ID in Pipeline CRM.

FRAMEWORKS

How to build Pipeline crm MCP Agent with another framework

Claude Code logo

Claude Code

Use Pipeline crm MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Pipeline crm MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Pipeline crm MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Pipeline crm MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Pipeline crm MCP with Grok Bot

Codex logo

Codex

Use Pipeline crm MCP with Codex

OpenClaw logo

OpenClaw

Use Pipeline crm MCP with OpenClaw

Hermes logo

Hermes

Use Pipeline crm MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Pipeline crm MCP with Atomic Agent

Google ADK logo

Google ADK

Use Pipeline crm MCP with Google ADK

LangChain logo

LangChain

Use Pipeline crm MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Pipeline crm MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Pipeline crm MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Pipeline crm MCP with LlamaIndex

CrewAI logo

CrewAI

Use Pipeline crm MCP with CrewAI

AutoGen logo

AutoGen

Use Pipeline crm MCP with AutoGen

FAQ

Frequently asked questions

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

Yes, you can. Pydantic AI 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 Pipeline crm tools.

Yes, absolutely. You can configure which Pipeline crm 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.

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 Pipeline crm data and credentials are handled as safely as possible.

Start with Pipeline crm.It takes 30 seconds.

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

Start building