How to integrate Convex MCP with Pydantic AI

This guide walks you through connecting Convex to Pydantic AI using the Composio tool router. By the end, you'll have a working Convex agent that can list records from convex tasks table, run convex query for active users, inspect convex deployment function logs through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Convex account through Composio's Convex MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Convex logoConvex
Api KeyBearer Token

Convex is a Backend-as-a-Service platform with a real-time database, serverless functions, and built-in authentication. Use it to build reactive apps faster without managing backend infrastructure.

19 Tools

Introduction

This guide walks you through connecting Convex to Pydantic AI using the Composio tool router. By the end, you'll have a working Convex agent that can list records from convex tasks table, run convex query for active users, inspect convex deployment function logs through natural language commands.

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

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

Also integrate Convex with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The Convex MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Convex account. It provides structured and secure access so your agent can perform Convex operations on your behalf.

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

Create deploy key

Tool to create a deploy key for use with the Convex CLI.

Create Deployment

Tool to create a new deployment for a Convex project.

Create Project

Tool to create a new project on a Convex team, optionally provisioning a dev or prod deployment.

Delete Custom Domain

Tool to remove a custom domain from a Convex deployment.

Delete Deployment

Tool to delete a Convex deployment.

Delete project

Deletes a Convex project and all its deployments permanently.

Execute Query Batch

Tool to execute multiple Convex query functions in a single batch request.

Get Deployment Details

Tool to retrieve details about a Convex cloud deployment.

Get Project by ID

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

Get Project by Slug

Tool to retrieve a Convex project by its slug within a team.

Get Query Timestamp

Tool to get the latest timestamp for queries from Convex deployment.

Get token details

Tool to retrieve token details for the authenticated token.

List Deploy Keys

Tool to list all deploy keys for a specified Convex deployment.

List deployment classes

Tool to list available deployment classes for a Convex team.

List deployment regions

Tool to list available deployment regions for a Convex team.

List Deployments

Tool to list all deployments for a Convex project.

List Log Streams

Tool to list all existing log stream configurations in a deployment.

List Projects

Tool to list all projects for a specific Convex team.

Update Deployment

Tool to update properties of an existing Convex deployment.

FRAMEWORKS

How to build Convex MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Convex MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Convex MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Convex MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Convex MCP with Claude Cowork

Codex logo

Codex

Use Convex MCP with Codex

OpenClaw logo

OpenClaw

Use Convex MCP with OpenClaw

Hermes logo

Hermes

Use Convex MCP with Hermes

CLI logo

CLI

Use Convex MCP with CLI

Google ADK logo

Google ADK

Use Convex MCP with Google ADK

LangChain logo

LangChain

Use Convex MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Convex MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Convex MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Convex MCP with LlamaIndex

CrewAI logo

CrewAI

Use Convex MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Convex.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies