How to integrate Salesflare MCP with Pydantic AI

Connect Pydantic AI to Salesflare MCP. List all contacts added this week, update deal stage for acme corp, and more using natural language, with authentication handled for you.

Salesflare logoSalesflare
Api Key

Salesflare is a CRM platform designed for B2B sales teams to manage pipelines and automate data entry. It helps businesses build better customer relationships with smart insights and effortless tracking.

63 Tools

Introduction

This guide walks you through connecting Salesflare to Pydantic AI using the Composio tool router. By the end, you'll have a working Salesflare agent that can list all contacts added this week, update deal stage for acme corp, create a new opportunity for globex through natural language commands.

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

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

Also integrate Salesflare with

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 Salesflare
  • 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 Salesflare 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 Salesflare MCP server, and what's possible with it?

The Salesflare MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Salesflare account. It provides structured and secure access to your accounts, contacts, opportunities, tasks, meetings, and calls, so your agent can manage customer records, track deals, schedule follow-ups, record sales activities, and review pipeline data on your behalf.

  • Account and contact management: Have your agent create, find, update, or remove contacts, and create, review, or update customer accounts.
  • Opportunity tracking: Let the agent create opportunities, review individual deals, filter your opportunity list, and update deals as they move through your pipeline.
  • Task and follow-up planning: Direct your agent to create sales tasks and list existing tasks using relevant filters so your team knows what to do next.
  • Meeting and call records: Instruct your agent to create meeting records and log one or more sales calls in Salesflare.
  • Team and CRM visibility: Have your agent review your contacts, accounts, team members, and current user details to gather the context needed for sales work.

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 Salesflare
  • 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 Salesflare
  • MCPServerStreamableHTTP connects to the Salesflare 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 Salesflare
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["salesflare"],
    )
    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 Salesflare 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
salesflare_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[salesflare_mcp],
    instructions=(
        "You are a Salesflare assistant. Use Salesflare tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Salesflare endpoint
  • The agent uses GPT-5 to interpret user commands and perform Salesflare 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 Salesflare.\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
  • Salesflare 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 Salesflare 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 Salesflare
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["salesflare"],
    )
    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
    salesflare_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[salesflare_mcp],
        instructions=(
            "You are a Salesflare assistant. Use Salesflare 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 Salesflare.\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 Salesflare through Composio's Tool Router. With this setup, your agent can perform real Salesflare 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 + Salesflare 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 Salesflare action and event your agent gets out of the box.

Add Account Contacts

Tool to add contacts to a specific account in Salesflare.

Create Account

Tool to create a new account in Salesflare.

Create call

Tool to create one or more call records in Salesflare.

Create Contact

Tool to create new contacts in Salesflare.

Create Custom Field

Creates a new custom field for accounts, contacts, or opportunities in Salesflare.

Create Internal Note

Tool to create an internal note in Salesflare associated with an account.

Create Meeting

Create a new meeting record in Salesflare.

Create Opportunity

Tool to create a new opportunity in Salesflare.

Create Tag

Tool to create a new tag in Salesflare.

Create Task

Tool to create a new task in Salesflare.

Create Workflow

Tool to create a new workflow (email automation sequence) in Salesflare.

Delete Account

Tool to permanently delete an account from Salesflare.

Delete Contact

Tool to delete a contact from Salesflare.

Delete Custom Field

Tool to delete a custom field from Salesflare.

Delete Internal Note

Tool to delete an internal note from Salesflare by its message ID.

Delete Meeting

Tool to delete a meeting from Salesflare.

Delete Opportunity

Tool to permanently delete an opportunity from Salesflare.

Delete Tag

Tool to delete a tag from Salesflare.

Delete Task

Tool to delete a task from Salesflare.

Get Account

Get detailed information about a specific account by ID.

Get AI Settings

Tool to retrieve AI settings for the Salesflare team.

Get Contact by ID

Retrieves detailed information for a specific contact by ID.

Get Current User

Tool to retrieve the details of the currently authenticated user.

Get Custom Field Details

Tool to retrieve details of a specific custom field.

Get Meeting Details

Tool to retrieve detailed information about a specific meeting by its ID.

Get Opportunity

Get detailed information about a specific opportunity by ID.

Get Stage

Get detailed information about a specific pipeline stage by ID.

Get Tag Usage

Get tag usage details including workflows, saved filters, and reports.

Get User

Tool to retrieve details of a specific user by their ID.

Get Workflow

Get detailed information about a specific workflow by ID.

Get Workflow Merge Fields

Tool to retrieve available merge fields for workflows in Salesflare.

List Account Messages

Tool to retrieve a list of messages associated with a specific account in Salesflare.

List accounts

Tool to list accounts with various filtering options including search, name, creation dates, size, domain, tags, address, and hotness level.

List Contacts

Tool to list contacts with filtering options.

List Supported Currencies

Tool to retrieve a list of supported currencies in Salesflare.

List Custom Field Options

Tool to list available options for a specific custom field in Salesflare.

List Custom Fields

Tool to list custom fields for a specified item class (accounts, contacts, or opportunities).

List Custom Field Types

Tool to retrieve a list of available custom field types in Salesflare.

List Email Data Sources

Tool to list email data sources.

List Filter Fields

Tool to list available filter fields for a specific entity type in Salesflare.

List Groups

Tool to list groups in Salesflare.

List My Contacts

Tool to list contacts belonging to the current user.

List Opportunities

Tool to list opportunities with extensive filtering options.

List Persons

Tool to list persons (non-contact people found in communications) from Salesflare.

List Pipelines

Tool to list pipelines in the Salesflare system with filtering and sorting options.

List Stages

Tool to list pipeline stages in the Salesflare system with filtering and sorting options.

List tags

Tool to list tags in the Salesflare system.

List Tasks

Tool to list tasks with filtering options.

List Users

Tool to list users (team members) in the Salesflare team.

List Workflows

Tool to list workflows (email automation sequences) in Salesflare.

Update Account

Tool to update an existing account in Salesflare.

Update Account Contacts

Tool to update the contacts associated with a specific Salesflare account.

Update Account Users

Tool to update the users associated with a specific Salesflare account.

Update AI Settings

Tool to update AI settings for the Salesflare team.

Update Contact

Tool to update an existing contact in Salesflare.

Update Custom Field

Updates an existing custom field for accounts, contacts, or opportunities in Salesflare.

Update Email Data Source

Tool to update the settings of an email data source in Salesflare.

Update Internal Note

Tool to update an existing internal note in Salesflare.

Update Opportunity

Tool to update an existing opportunity in Salesflare.

Update Tag

Tool to update the name of an existing tag in Salesflare.

Update Task

Tool to update an existing task in Salesflare.

Update Workflow

Tool to update an existing workflow in Salesflare.

Update Workflow Audience

Tool to re-enter or exit an entity from a workflow in Salesflare.

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Salesflare 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 Salesflare data and credentials are handled as safely as possible.

Start with Salesflare.It takes 30 seconds.

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

Start building