How to integrate Bitquery MCP with Pydantic AI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Bitquery Logo
Pydantic AI Logo
divider

Introduction

This guide walks you through connecting Bitquery to Pydantic AI using the Composio tool router. By the end, you'll have a working Bitquery agent that can show real-time ethereum mempool transactions, count unique wallet addresses for solana, query historical bitcoin transactions from 2021, aggregate all erc20 transfers on polygon today through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Bitquery account through Composio's Bitquery 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:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Bitquery
  • 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 Bitquery 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 Bitquery MCP server, and what's possible with it?

The Bitquery MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bitquery account. It provides structured and secure access to blockchain datasets and real-time analytics, so your agent can perform actions like querying historical transactions, streaming mempool activity, selecting blockchain networks, and aggregating metrics across 40+ supported chains.

  • Seamless blockchain data querying: Let your agent run powerful queries on historical or real-time blockchain data across multiple networks using Bitquery's combined or archive databases.
  • Live mempool monitoring: Subscribe and stream pending transactions from EVM-compatible chains in real time, enabling instant insights into network activity as it happens.
  • On-demand network and database selection: Have your agent dynamically select blockchain networks and datasets—like Ethereum, BNB Chain, or others—to tailor queries for your specific use case.
  • Metric aggregation and analysis: Automate the aggregation of transaction counts, unique values, or conditional metrics, empowering your agent to analyze blockchain trends without manual intervention.
  • Advanced GraphQL customization: Use aliases and conditional snippets to refine data responses, ensuring clarity and precise control in complex blockchain analytics workflows.

Supported Tools & Triggers

Tools
Aliases MetricTool to use graphql aliases to rename fields in the response for clarity and disambiguation.
Archive Database QueryTool to query the archive database.
Combined Database QueryTool to query the combined database, which merges archive and real-time databases.
Conditional Metrics SnippetTool to generate a graphql metric snippet with conditional logic.
Count Distinct MetricTool to use the count distinct metric to aggregate unique values for a field.
Count MetricTool to use the count metric to aggregate the number of records matching a graphql query.
Database SelectionTool to select the database (archive, realtime, combined) to query at the top level of a graphql request.
Early Access Program QueryTool to access streaming data across various blockchain networks for evaluation purposes.
Mempool SubscriptionTool to subscribe to real-time mempool updates for evm chains (ethereum, bnb, etc.
Network SelectionTool to select the blockchain network for graphql queries.
Options QueryTool to fetch graphql dataset options via schema introspection.
Price Asymmetry MetricTool to generate graphql priceasymmetry filter snippet.
Quantile MetricTool to calculate quantiles to understand the distribution of numerical data.
Realtime Database QueryRealtime database query
Select By MetricTool to generate a graphql metric snippet filtering by its value using selectwhere.
Statistics MetricTool to compute statistical metrics (mean, median, etc.
Sum MetricTool to calculate the sum of a specified field's values across defined dimensions.
Uniq MetricTool to estimate the count of unique values using the uniq metric.

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:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming

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.

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 Bitquery
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file

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

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 Bitquery
  • MCPServerStreamableHTTP connects to the Bitquery MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

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 Bitquery
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bitquery"],
    )
    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 Bitquery 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

Initialize the Pydantic AI Agent

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

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 Bitquery.\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
  • Bitquery API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

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 Bitquery and Pydantic AI:

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 Bitquery
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["bitquery"],
    )
    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
    bitquery_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[bitquery_mcp],
        instructions=(
            "You are a Bitquery assistant. Use Bitquery 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 Bitquery.\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 Bitquery through Composio's Tool Router. With this setup, your agent can perform real Bitquery 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 + Bitquery for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Bitquery MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Bitquery MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Bitquery MCP with Claude Agent SDK

Google ADK

Google ADK

Use Bitquery MCP with Google ADK

LangChain

LangChain

Use Bitquery MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Bitquery MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Bitquery MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Bitquery MCP with LlamaIndex

CrewAI

CrewAI

Use Bitquery MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Pydantic AI?

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 Bitquery tools.

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

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

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
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 call↗Get started for free