# How to integrate Anchor browser MCP with Pydantic AI

```json
{
  "title": "How to integrate Anchor browser MCP with Pydantic AI",
  "toolkit": "Anchor browser",
  "toolkit_slug": "anchor_browser",
  "framework": "Pydantic AI",
  "framework_slug": "pydantic-ai",
  "url": "https://composio.dev/toolkits/anchor_browser/framework/pydantic-ai",
  "markdown_url": "https://composio.dev/toolkits/anchor_browser/framework/pydantic-ai.md",
  "updated_at": "2026-05-12T10:01:12.416Z"
}
```

## Introduction

This guide walks you through connecting Anchor browser to Pydantic AI using the Composio tool router. By the end, you'll have a working Anchor browser agent that can fetch full content of a product page, list all active browser sessions now, get details for a specific browser profile through natural language commands.
This guide will help you understand how to give your Pydantic AI agent real control over a Anchor browser account through Composio's Anchor browser MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Anchor browser with

- [OpenAI Agents SDK](https://composio.dev/toolkits/anchor_browser/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/anchor_browser/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/anchor_browser/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/anchor_browser/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/anchor_browser/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/anchor_browser/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/anchor_browser/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/anchor_browser/framework/cli)
- [Google ADK](https://composio.dev/toolkits/anchor_browser/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/anchor_browser/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/anchor_browser/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/anchor_browser/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/anchor_browser/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/anchor_browser/framework/crew-ai)

## 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 Anchor browser
- 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 Anchor browser 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 Anchor browser MCP server, and what's possible with it?

The Anchor browser MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Anchor browser account. It provides structured and secure access to powerful web automation features, so your agent can fetch web content, manage browser sessions, control profiles, and interact with extensions on your behalf.
- Automated webpage content retrieval: Instruct your agent to browse to any URL and fetch the fully rendered page content in HTML or markdown, enabling easy scraping or summarization.
- Session and profile management: Let your agent create, list, or delete browser profiles, as well as start, end, or monitor multiple browsing sessions for different workflows or user contexts.
- Browser extension control: Have the agent list all installed browser extensions, making it easy to audit and manage your browser environment programmatically.
- Resource and file listing: Ask your agent to retrieve a list of files or resources uploaded during browser automation tasks, ensuring nothing gets lost in the shuffle.
- Comprehensive session oversight: Quickly get an overview of all active browser sessions, their statuses, and terminate any or all sessions instantly for security or resource management needs.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `ANCHOR_BROWSER_CLICK_MOUSE` | Click Mouse | Tool to perform a mouse click at specified coordinates within a browser session. Use when you need to interact with page elements by clicking at specific x/y positions. The click is executed in the context of the specified browser session. |
| `ANCHOR_BROWSER_COPY_SELECTED_TEXT` | Copy Selected Text | Tool to copy currently selected text in a browser session to the clipboard. Use when you need to extract text that the user or automation has selected in the browser. |
| `ANCHOR_BROWSER_CREATE_INTEGRATION` | Create Integration | Tool to create a new integration with a third-party service like 1Password. Use when you need to set up an integration for managing credentials or accessing external services. The integration will be available immediately after creation for use in browser sessions and profiles. |
| `ANCHOR_BROWSER_CREATE_OR_UPDATE_TASK_DRAFT` | Create or Update Task Draft | Tool to create or update the draft version of a task. Draft versions are used for development and testing before publishing. Use when you need to save task code changes without creating a published version. |
| `ANCHOR_BROWSER_CREATE_PROFILE` | Create Profile | Creates a new browser profile from an active session. A profile stores cookies, local storage, and cache data. The session must be running when this is called; profile data is persisted once the session terminates. Use profiles to maintain persistent browser state across multiple sessions. |
| `ANCHOR_BROWSER_CREATE_TASK` | Create Task | Tool to create a new task or update an existing task with the same name. Tasks are reusable TypeScript code snippets that execute in browser sessions. Use when you need to define repeatable automation workflows that can be invoked across multiple sessions. |
| `ANCHOR_BROWSER_DELETE_EXTENSION` | Delete Extension | Tool to delete a browser extension and remove it from storage. Use after confirming the extension exists. |
| `ANCHOR_BROWSER_DELETE_INTEGRATION` | Delete Integration | Tool to delete an existing integration and remove its stored credentials. Use after confirming the integration ID exists. |
| `ANCHOR_BROWSER_DELETE_PROFILE` | Delete Profile | Tool to delete a browser profile by ID. Use after confirming the profile exists. |
| `ANCHOR_BROWSER_DELETE_TASK` | Delete Task | Tool to soft delete a task and all its versions. Use after confirming the task exists. |
| `ANCHOR_BROWSER_DELETE_TASK_VERSION` | Delete Task Version | Tool to soft delete a specific version of a task. The version will no longer be accessible but data is preserved for recovery. Use when you need to remove a specific task version. |
| `ANCHOR_BROWSER_DEPLOY_TASK` | Deploy Task | Tool to deploy a task by creating a new version with auto-incremented version number. Use when you need to publish task changes and make them available for execution. |
| `ANCHOR_BROWSER_DOUBLE_CLICK_MOUSE` | Double Click Mouse | Tool to perform a double click at specified coordinates in a browser session. Use when you need to trigger double-click events on UI elements or specific page locations. |
| `ANCHOR_BROWSER_DRAG_AND_DROP` | Drag and Drop | Tool to perform a drag and drop operation from start coordinates to end coordinates within a browser session. Use when you need to simulate dragging UI elements or files in automated workflows. |
| `ANCHOR_BROWSER_END_ALL_SESSIONS` | End All Sessions | Tool to terminate all active browser sessions at once. Use when you need to immediately close every browser session for the authenticated user, such as during cleanup operations or security concerns. |
| `ANCHOR_BROWSER_END_BROWSER_SESSION` | End Browser Session | Tool to end a specific browser session by ID. Use after confirming the session ID you want to terminate. |
| `ANCHOR_BROWSER_GET_BATCH_SESSION_STATUS` | Get Batch Session Status | Tool to retrieve detailed status information for a specific batch including progress and errors. Use when you need to check the status of a batch session creation request. |
| `ANCHOR_BROWSER_GET_BROWSER_SESSION` | Get Browser Session | Tool to retrieve detailed information about a specific browser session. Use when you need to check the status, configuration, or execution details of a browser session. |
| `ANCHOR_BROWSER_GET_CLIPBOARD_CONTENT` | Get Clipboard Content | Tool to retrieve the current content of the clipboard from a browser session. Use when you need to read clipboard data from an active session. |
| `ANCHOR_BROWSER_GET_LATEST_TASK_VERSION` | Get Latest Task Version | Tool to retrieve the latest version of a task including the full base64 encoded code content. Use when you need to access the most recent task implementation. |
| `ANCHOR_BROWSER_GET_PROFILE2` | Get Profile (v2) | Tool to retrieve details of a specific profile by its name. Use when you need to fetch information about a particular browser profile. |
| `ANCHOR_BROWSER_GET_SESSION_PAGES` | Get Session Pages | Tool to retrieve all pages associated with a specific browser session. Use when you need to list all open tabs or pages in an active or completed session. |
| `ANCHOR_BROWSER_GET_TASK_DRAFT` | Get Task Draft | Tool to retrieve the draft version of a task, including the full Base64 encoded code content. Use when you need to access the current draft of a task that hasn't been published yet. |
| `ANCHOR_BROWSER_GET_TASK_EXECUTION_RESULT` | Get Task Execution Result | Tool to retrieve a single task execution result by its ID. Use when you need to check the status, output, or error details of a specific task execution. |
| `ANCHOR_BROWSER_GET_TASK_METADATA` | Get Task Metadata | Tool to retrieve task metadata without downloading the full task code. Use when you need task information such as status, creation time, or language without the code content. |
| `ANCHOR_BROWSER_GET_TASK_VERSION` | Get Task Version | Tool to retrieve a specific version of a task, including the full code content. Use when you need to access the complete task code for a particular version (draft, latest, or specific version number). |
| `ANCHOR_BROWSER_GET_WEBPAGE_CONTENT` | Get Webpage Content | Tool to retrieve rendered content of a webpage in HTML or Markdown format. Use when you need to fetch a page’s full content, optionally within an existing browser session. |
| `ANCHOR_BROWSER_LIST_AGENT_RESOURCES` | List Agent Resources | List all agent resources (files) uploaded to a browser session. Returns metadata for each file including name, size, file type, and last modified timestamp. Requires an active running session - use START_BROWSER_SESSION first. Files can be uploaded using UPLOAD_FILE action. |
| `ANCHOR_BROWSER_LIST_EXTENSIONS` | List Extensions | Retrieves all browser extensions uploaded by the authenticated user. Use this to view available extensions that can be attached to browser sessions for automation tasks. |
| `ANCHOR_BROWSER_LIST_INTEGRATIONS` | List Integrations | Tool to retrieve all integrations for the authenticated team. Use when you need to view available integrations that can be used with browser sessions. |
| `ANCHOR_BROWSER_LIST_PROFILES` | List Profiles | Tool to fetch all stored browser profiles. Use when you need an overview of all profiles available to the authenticated user (e.g., after creating or deleting profiles). |
| `ANCHOR_BROWSER_LIST_SESSION_DOWNLOADS` | List Session Downloads | Tool to retrieve metadata of files downloaded during a browser session. Use after confirming the session ID. |
| `ANCHOR_BROWSER_LIST_SESSION_RECORDINGS` | List Session Recordings | Tool to list all recordings for a specific browser session. Use after confirming the session ID. |
| `ANCHOR_BROWSER_LIST_SESSIONS` | List Sessions | Tool to list all browser sessions. Use when you need to retrieve both active and inactive sessions. |
| `ANCHOR_BROWSER_LIST_TASK_EXECUTIONS` | List Task Executions | Tool to retrieve execution history for a specific task with filtering and pagination support. Use when you need to view past execution results, monitor task success rates, or debug failed executions. |
| `ANCHOR_BROWSER_LIST_TASKS` | List Tasks | Tool to retrieve a paginated list of all tasks for the authenticated team. Use when you need to view available tasks with their latest version information and metadata. |
| `ANCHOR_BROWSER_LIST_TASK_VERSIONS` | List Task Versions | Tool to retrieve all versions of a specific task, including draft and published versions. Use when you need to view the version history of a task or select a specific version for deployment or execution. |
| `ANCHOR_BROWSER_MOVE_MOUSE` | Mouse Move | Tool to move the mouse cursor to specified coordinates within a browser session. Use when you need to simulate mouse movement at the OS level. |
| `ANCHOR_BROWSER_NAVIGATE_TO_URL` | Navigate to URL | Tool to navigate a browser session to a specified URL. Use when you need to direct an existing session to a new webpage. |
| `ANCHOR_BROWSER_PASTE_TEXT` | Paste Text | Tool to paste text at the current cursor position in a browser session. Use when you need to insert text into an active form field or text area. |
| `ANCHOR_BROWSER_PAUSE_AGENT` | Pause Agent | Tool to pause the AI agent for a specific browser session. Use when you need to temporarily halt autonomous agent execution while keeping the session active. |
| `ANCHOR_BROWSER_PAUSE_SESSION_RECORDING` | Pause Session Recording | Tool to pause the video recording for a specific browser session. Use when you need to temporarily stop recording without ending the session. |
| `ANCHOR_BROWSER_PERFORM_KEYBOARD_SHORTCUT` | Perform Keyboard Shortcut | Tool to perform a keyboard shortcut using specified keys in a browser session. Use when you need to simulate keyboard input like copy (Control+C), paste (Control+V), or any other key combination. |
| `ANCHOR_BROWSER_PERFORM_WEB_TASK` | Perform Web Task | Tool to perform autonomous web tasks using AI agents. Use when you need to automate complex browser interactions like form filling, data extraction, or multi-step workflows. |
| `ANCHOR_BROWSER_PRESS_MOUSE_BUTTON` | Mouse Down | Tool to perform a mouse button down action at specified coordinates within a browser session. Use when you need to simulate pressing and holding a mouse button at a specific screen position. |
| `ANCHOR_BROWSER_PUBLISH_TASK_VERSION` | Publish Task Version | Tool to publish a specific version of a task. Creates a new version if it doesn't exist, or updates an existing version's metadata. Use when you need to make a specific task version available for execution. Cannot publish to 'draft' versions. |
| `ANCHOR_BROWSER_RELEASE_MOUSE_BUTTON` | Release Mouse Button | Tool to release a mouse button at specified coordinates within a browser session. Use when automating mouse interactions that require button release events, such as completing drag operations or simulating natural mouse behavior. |
| `ANCHOR_BROWSER_RESUME_AGENT` | Resume Agent | Tool to resume the AI agent for a specific browser session. Use when you need to restart agent execution after it has been paused or stopped. |
| `ANCHOR_BROWSER_RESUME_SESSION_RECORDING` | Resume Session Recording | Tool to resume video recording for a specific browser session. Use when recording was previously paused and needs to be restarted. |
| `ANCHOR_BROWSER_RUN_TASK` | Run Task | Tool to execute a task in a browser session with a specific or latest version. Use when you need to run an existing task with optional session reuse and configuration overrides. |
| `ANCHOR_BROWSER_RUN_TASK_BY_NAME` | Run Task by Name | Tool to execute a task by its name, always using the latest version. Use when you need to run a predefined browser automation task by referencing its name. |
| `ANCHOR_BROWSER_SCREENSHOT_WEBPAGE` | Screenshot Webpage | Tool to take a screenshot of a specified webpage within a session. Use when you need a visual PNG snapshot of a live page. Example: "Capture a 1280×720 screenshot of https://example.com". |
| `ANCHOR_BROWSER_SCROLL_SESSION` | Scroll Session | Tool to perform a scroll action at specified coordinates within a browser session. Use when you need to scroll to specific positions or simulate user scrolling behavior. Example: "Scroll down 100 pixels from position (100, 100) in session sess_123". |
| `ANCHOR_BROWSER_SET_CLIPBOARD_CONTENT` | Set Clipboard Content | Tool to set the content of the clipboard in a browser session. Use when you need to programmatically copy text to the clipboard for automated workflows. |
| `ANCHOR_BROWSER_SIGNAL_EVENT` | Signal Event | Tool to signal a specific event to be received by other processes or sessions. Use when you need real-time coordination across browser sessions after verifying session is active. |
| `ANCHOR_BROWSER_START_BROWSER_SESSION` | Start Browser Session | Tool to start a new browser session with optional customizations. Use when you need to programmatically allocate an isolated browser instance with recording, proxy, live view, and feature toggles. |
| `ANCHOR_BROWSER_TAKE_SCREENSHOT` | Take Screenshot | Tool to take a screenshot of the current browser session and return it as an image. Use when you need a visual snapshot of an active browser session. |
| `ANCHOR_BROWSER_TYPE_TEXT` | Type Text | Tool to type specified text with optional delay between keystrokes. Use when you need to input text into a browser session, such as filling forms or entering search queries. |
| `ANCHOR_BROWSER_UPDATE_PROFILE` | Update Profile | Updates an existing browser profile with data from an active session. The profile stores cookies, local storage, and cache from the session. Requires an active (running) browser session - the session_id must reference a session that has not been terminated. |
| `ANCHOR_BROWSER_UPDATE_TASK_METADATA` | Update Task Metadata | Updates task metadata (name and description). This does not affect the task code or versions. Use when you need to update task information without modifying the implementation. |
| `ANCHOR_BROWSER_UPLOAD_EXTENSION` | Upload Extension | Tool to upload a new browser extension as a ZIP file for use in browser sessions. Use when you need to add custom extensions that can be attached to automation sessions. The ZIP file must contain a valid extension manifest (manifest.json). Extensions are scoped to the authenticated user and can be listed or attached to sessions later. |
| `ANCHOR_BROWSER_UPLOAD_FILE` | Upload File | Tool to upload a file to a browser session as an agent resource. Use after starting or referencing a session when you need to provide file inputs (single files or ZIP archives) for web forms or AI-driven tasks. Supports direct base64-encoded content or S3 key references from other actions. |
| `ANCHOR_BROWSER_UPLOAD_FILES_TO_SESSION` | Upload Files to Session | Tool to upload files directly to a browser session for use with web forms and file inputs. Use when you need to provide file inputs to web forms during automated browser sessions. |
| `ANCHOR_BROWSER_WAIT_FOR_EVENT` | Wait for Event | Blocks execution until a specific named event is signaled or the timeout expires. Used for cross-session coordination, MFA handling, and workflow synchronization. The event must first be signaled using the Signal Event action. Returns the data payload that was sent with the signal. Events are user-scoped. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Anchor browser MCP server is an implementation of the Model Context Protocol that connects your AI agent to Anchor browser. It provides structured and secure access so your agent can perform Anchor browser operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 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

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

Install the required libraries.
What's happening:
- composio connects your agent to external SaaS tools like Anchor browser
- pydantic-ai lets you create structured AI agents with tool support
- python-dotenv loads your environment variables securely from a .env file
```bash
pip install composio pydantic-ai python-dotenv
```

### 3. Set up environment variables

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
```bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key
```

### 4. Import dependencies

What's happening:
- We load environment variables and import required modules
- Composio manages connections to Anchor browser
- MCPServerStreamableHTTP connects to the Anchor browser MCP server endpoint
- Agent from Pydantic AI lets you define and run the AI assistant
```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()
```

### 5. Create a Tool Router Session

What's happening:
- We're creating a Tool Router session that gives your agent access to Anchor browser 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
```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 Anchor browser
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["anchor_browser"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
```

### 6. Initialize the Pydantic AI Agent

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

### 7. Build the chat interface

What's happening:
- The agent reads input from the terminal and streams its response
- Anchor browser API calls happen automatically under the hood
- The model keeps conversation history to maintain context across turns
```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 Anchor browser.\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()
```

### 8. Run the application

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

## Complete Code

```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 Anchor browser
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["anchor_browser"],
    )
    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
    anchor_browser_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[anchor_browser_mcp],
        instructions=(
            "You are a Anchor browser assistant. Use Anchor browser 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 Anchor browser.\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 Anchor browser through Composio's Tool Router. With this setup, your agent can perform real Anchor browser 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 + Anchor browser 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 Anchor browser MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/anchor_browser/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/anchor_browser/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/anchor_browser/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/anchor_browser/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/anchor_browser/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/anchor_browser/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/anchor_browser/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/anchor_browser/framework/cli)
- [Google ADK](https://composio.dev/toolkits/anchor_browser/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/anchor_browser/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/anchor_browser/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/anchor_browser/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/anchor_browser/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/anchor_browser/framework/crew-ai)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.
- [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data.
- [Bolt iot](https://composio.dev/toolkits/bolt_iot) - Bolt IoT is a platform for building and managing IoT projects with cloud-based device control and monitoring. It makes connecting sensors and actuators to the internet seamless for automation and data insights.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Anchor browser MCP?

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

### Can I manage the permissions and scopes for Anchor browser while using Tool Router?

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

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)