# How to integrate Anchor browser MCP with LlamaIndex

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

## Introduction

This guide walks you through connecting Anchor browser to LlamaIndex 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 LlamaIndex 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)
- [CrewAI](https://composio.dev/toolkits/anchor_browser/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Anchor browser
- Connect LlamaIndex to the Anchor browser MCP server
- Build a Anchor browser-powered agent using LlamaIndex
- Interact with Anchor browser through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built 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 you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Anchor browser account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Anchor browser

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Anchor browser access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, anchor browser)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Anchor browser tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["anchor_browser"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Anchor browser actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Anchor browser actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["anchor_browser"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Anchor browser actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Anchor browser
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Anchor browser, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["anchor_browser"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Anchor browser actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Anchor browser actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["anchor_browser"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Anchor browser actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Anchor browser to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Anchor browser tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## 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)
- [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 LlamaIndex?

Yes, you can. LlamaIndex 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)