SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Parsera MCP with Pydantic AI

Connect Pydantic AI to Parsera MCP. Extract all headers from this blog post, get product names and prices from a webpage, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Parsera logoParsera
Api Key

Parsera is a lightweight Python library for scraping websites using large language models (LLMs). It enables fast, structured web data extraction without complex manual scripting.

14 Tools

Introduction

This guide walks you through connecting Parsera to Pydantic AI using the Composio tool router. By the end, you'll have a working Parsera agent that can extract data from webpages, convert pages to Markdown, create and run scrapers, check scraper run status, and manage agents through natural language commands.

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

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

Also integrate Parsera with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic 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 Parsera
  • 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 Parsera 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 Parsera MCP server, and what's possible with it?

The Parsera MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Parsera account. It provides structured and secure access to website content, so your agent can extract markdown, parse structured data, and automate web scraping workflows on your behalf.

  • Extract markdown from webpages: Ask your agent to pull clean, readable markdown content directly from any public URL or file.
  • Parse and structure HTML content: Let your agent analyze raw HTML or text and convert it into structured data you can use for downstream tasks.
  • Automate data extraction workflows: Direct your agent to combine fetching, parsing, and formatting steps to streamline web scraping projects end-to-end.
  • Simplify report and content generation: Have your agent turn scraped website data into markdown reports or ready-to-use documentation for your projects.

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

Create Scraper

Tool to create a new empty scraper for your account.

Delete Agent

Delete an existing legacy Parsera agent by name.

Delete Scraper

Delete an existing scraper by ID using Parsera's legacy scraper deletion endpoint.

Extract Data from Webpage

Tool to perform LLM-powered data extraction from a live webpage URL with specified attributes.

Extract Markdown

Extract markdown from exactly one uploaded file or webpage URL.

Get Scraper Run Status

Return the current state and available results for a scraper run by run ID, including a synchronous run continued asynchronously.

List Agents

List the authenticated user's agents from Parsera's legacy agent service.

List LLM Specifications

List the LLM models Parsera supports, including their capabilities and pricing metadata.

List Proxy Countries

List the case-sensitive proxy-country identifiers accepted by Parsera scraping tools.

List Scrapers

List scraper IDs and names for the authenticated account, including extractor and agentic scrapers.

Parse Content

Extract structured data from supplied HTML or text without fetching a webpage.

Run Legacy Agent

Run a custom or pre-built agent from Parsera's legacy agent service against one webpage and return structured records.

Run Scraper Asynchronously

Queue an existing extractor or agentic scraper and return a run ID immediately for later status checks.

Run Scraper Synchronously

Run an existing Parsera template or legacy scraper synchronously.

FRAMEWORKS

How to build Parsera MCP Agent with another framework

Claude Code logo

Claude Code

Use Parsera MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Parsera MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Parsera MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Parsera MCP with Claude Agent SDK

Codex logo

Codex

Use Parsera MCP with Codex

OpenClaw logo

OpenClaw

Use Parsera MCP with OpenClaw

Hermes logo

Hermes

Use Parsera MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Parsera MCP with Atomic Agent

Google ADK logo

Google ADK

Use Parsera MCP with Google ADK

LangChain logo

LangChain

Use Parsera MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Parsera MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Parsera MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Parsera MCP with LlamaIndex

CrewAI logo

CrewAI

Use Parsera MCP with CrewAI

AutoGen logo

AutoGen

Use Parsera MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Parsera.It takes 30 seconds.

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

Start building