# How to integrate Studio By Ai21 Labs MCP with LlamaIndex

```json
{
  "title": "How to integrate Studio By Ai21 Labs MCP with LlamaIndex",
  "toolkit": "Studio By Ai21 Labs",
  "toolkit_slug": "studio_by_ai21_labs",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/studio_by_ai21_labs/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/studio_by_ai21_labs/framework/llama-index.md",
  "updated_at": "2026-03-29T06:52:00.301Z"
}
```

## Introduction

This guide walks you through connecting Studio By Ai21 Labs to LlamaIndex using the Composio tool router. By the end, you'll have a working Studio By Ai21 Labs agent that can generate a summary of this research paper, classify sentiment of this product review, extract key topics from meeting transcript through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Studio By Ai21 Labs account through Composio's Studio By Ai21 Labs MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Studio By Ai21 Labs with

- [OpenAI Agents SDK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/studio_by_ai21_labs/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/studio_by_ai21_labs/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/studio_by_ai21_labs/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/studio_by_ai21_labs/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/studio_by_ai21_labs/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/studio_by_ai21_labs/framework/cli)
- [Google ADK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/studio_by_ai21_labs/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/studio_by_ai21_labs/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/studio_by_ai21_labs/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 Studio By Ai21 Labs
- Connect LlamaIndex to the Studio By Ai21 Labs MCP server
- Build a Studio By Ai21 Labs-powered agent using LlamaIndex
- Interact with Studio By Ai21 Labs 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 Studio By Ai21 Labs MCP server, and what's possible with it?

The Studio By Ai21 Labs MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Studio By Ai21 Labs account. It provides structured and secure access so your agent can perform Studio By Ai21 Labs operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `STUDIO_BY_AI21_LABS_CHECK_CAN_IFRAME` | Check Can Iframe | Tool to check if a URL can be embedded in an iframe. Use when you need to verify iframe compatibility before embedding external content. |
| `STUDIO_BY_AI21_LABS_COMPARE_TEXT` | Compare Text | Tool to compare two text strings and identify differences. Use when you need to analyze changes between an original text and its modified version. |
| `STUDIO_BY_AI21_LABS_CREATE_AFTERSALES_PARTS_BATCH` | Create Aftersales Parts Classification Batch | Tool to create a batch job for Fnac Aftersales parts classification. Use when you need to classify multiple aftersales cases to determine which parts are needed for repairs. |
| `STUDIO_BY_AI21_LABS_CREATE_ASSISTANT_ROUTE` | Create Assistant Route | Tool to create a new route for an AI21 Studio assistant. Use when you need to define a new conversational path or query pattern for an assistant. |
| `STUDIO_BY_AI21_LABS_CREATE_ASSISTANT` | Create Assistant | Tool to create a new AI assistant in AI21 Studio. Use when you need to set up a new assistant with custom configuration, tools, and behavior. |
| `STUDIO_BY_AI21_LABS_CREATE_ASSISTANT_PLAN` | Create Assistant Plan | Tool to create a new plan for an AI21 Studio assistant. Use when you need to add a new plan with Python code to an assistant. |
| `STUDIO_BY_AI21_LABS_CREATE_DEMO` | Create Demo | Tool to create a new demo in AI21 Studio. Use when you need to set up a new demo with specified visibility and status. |
| `STUDIO_BY_AI21_LABS_GENERATE_REQUIREMENTS` | Generate Requirements | Tool to generate requirements from a query or task description. Use when you need to break down a high-level task into specific requirements. |
| `STUDIO_BY_AI21_LABS_GENERATE_THREAD_NAME` | Generate Thread Name | Tool to generate a thread name from a query or conversation context. Use when you need to create a descriptive title for a conversation thread. |
| `STUDIO_BY_AI21_LABS_CREATE_KIRSH_GRANT_COMPLIANCE_PREVIEW` | Create Kirsh Grant Compliance Preview | Tool to preview grant compliance for Kirsh grants. Use when you need to check compliance status for specific grant IDs. |
| `STUDIO_BY_AI21_LABS_KIRSH_GRANT_METADATA_PREVIEW` | Kirsh Grant Metadata Preview | Tool to retrieve grant metadata from the Kirsh preview endpoint. Use when you need to fetch grant information including grant name and associated organization details. |
| `STUDIO_BY_AI21_LABS_CREATE_MCP_STORAGE` | Create MCP Storage | Tool to create MCP (Model Context Protocol) storage in AI21 Studio. Use when you need to register and configure an MCP server connection for your workspace. |
| `STUDIO_BY_AI21_LABS_CREATE_SECRET` | Create Secret | Tool to save a secret in AI21 Studio. Use when you need to securely store sensitive information like API keys or passwords. |
| `STUDIO_BY_AI21_LABS_CHECK_KIRSH_GRANT_COMPLIANCE` | Check Kirsh Grant Compliance | Tool to check compliance for Kirsh grant IDs. Use when you need to verify compliance status for one or more grants. |
| `STUDIO_BY_AI21_LABS_CREATE_WEBSITE_CONNECTOR` | Create Website Connector | Tool to create a website connector in AI21 Studio. Use when you need to index website content via sitemap or specific URLs for RAG or grounding purposes. |
| `STUDIO_BY_AI21_LABS_DELETE_ASSISTANT` | Delete Assistant | Tool to delete an assistant by its unique ID. Use when you need to permanently remove an assistant from the system. |
| `STUDIO_BY_AI21_LABS_DELETE_ASSISTANT_ROUTE` | Delete Assistant Route | Tool to delete a route from an AI21 Studio assistant. Use when you need to remove a routing configuration from an assistant. |
| `STUDIO_BY_AI21_LABS_DELETE_DEMO` | Delete Demo | Tool to delete a demo by its unique ID. Use when removing a specific demo from AI21 Studio. |
| `STUDIO_BY_AI21_LABS_DELETE_MCP_STORAGE` | Delete MCP Storage | Tool to delete an MCP (Model Context Protocol) storage configuration by its unique ID. Use when you need to permanently remove an MCP server configuration from AI21 Studio. |
| `STUDIO_BY_AI21_LABS_DELETE_SECRET` | Delete Secret | Tool to delete a secret by its unique ID. Use when you need to permanently remove a secret from AI21 Studio. |
| `STUDIO_BY_AI21_LABS_DELETE_WEBSITE_CONNECTOR` | Delete Website Connector | Permanently delete a website connector by its unique identifier. Use when you need to remove a website connector that is no longer needed. |
| `STUDIO_BY_AI21_LABS_DOWNLOAD_MODIFIED_DOCUMENT` | Download Modified Document | Tool to download a modified document from AI21 Labs Studio. Use when you need to generate and download a document with specific content and filename. |
| `STUDIO_BY_AI21_LABS_GET_ASSISTANT` | Get Assistant | Tool to retrieve an assistant by its unique identifier. Use when you need to get details about a specific assistant including its configuration, tools, and settings. |
| `STUDIO_BY_AI21_LABS_GET_ASSISTANT_ROUTE` | Get Assistant Route | Tool to retrieve details of a specific route for an AI21 Studio assistant. Use when you need to get information about a particular route configuration. |
| `STUDIO_BY_AI21_LABS_GET_ASSISTANTS_BY_MCP` | Get Assistants By MCP | Tool to retrieve all assistants associated with a specific MCP (Model Context Protocol) storage configuration. Use when you need to list assistants that are connected to a particular MCP server. |
| `STUDIO_BY_AI21_LABS_GET_BATCH_PREDICTION_STATUS` | Get Batch Prediction Status | Tool to check the status of a Fnac Aftersales parts classification batch prediction job. Use when you need to monitor the progress or retrieve results of a previously submitted batch. |
| `STUDIO_BY_AI21_LABS_GET_DEMO` | Get Demo | Tool to retrieve a demo by its unique ID. Use when you need to fetch details about a specific demo including its name, status, visibility, and configuration. |
| `STUDIO_BY_AI21_LABS_GRANT_KIRSH_METADATA` | Grant Kirsh Metadata | Tool to retrieve Kirsh grant metadata by grant ID. Use when you need to fetch grant information including grant name and organization details. |
| `STUDIO_BY_AI21_LABS_GET_LIBRARY_BATCH_STATUS` | Get Library Batch Status | Tool to get the ingestion status of a library batch. Use when you need to check the processing status of documents in a batch upload. |
| `STUDIO_BY_AI21_LABS_GET_MCP_STORAGE` | Get MCP Storage | Tool to retrieve a specific MCP (Model Context Protocol) storage configuration by its unique ID. Use when you need to get details about a particular MCP server including its URL, label, authentication settings, and allowed tools. |
| `STUDIO_BY_AI21_LABS_GET_OUTPUT_EXPLANATION` | Get Output Explanation | Tool to get output explanation for an execution (cached or generated). Use when you need to retrieve or regenerate the explanation for a specific execution. Set force_regenerate to true to bypass cache. |
| `STUDIO_BY_AI21_LABS_GET_PLAN` | Get Plan | Tool to retrieve a specific plan from an AI21 Studio assistant. Use when you need to fetch details of a plan by its ID. |
| `STUDIO_BY_AI21_LABS_GET_WEBSITE_CONNECTOR_BY_ID` | Get Website Connector By ID | Tool to retrieve details of a specific website connector by its ID. Use when you need to fetch information about a website connector in AI21 Studio. |
| `STUDIO_BY_AI21_LABS_GET_WEBSITE_CONNECTOR_STATUS` | Get Website Connector Status | Tool to retrieve the status of a website connector ingestion. Use when you need to check the processing status of a website that was added to AI21 Studio. |
| `STUDIO_BY_AI21_LABS_GET_WEBSITE_CONNECTOR_URL_STATUS` | Get Website Connector URL Status | Tool to retrieve the status of a specific URL in the website connector. Use when you need to check the processing status of a URL that was previously ingested. |
| `STUDIO_BY_AI21_LABS_INGEST_WEBSITE_CONNECTOR` | Ingest Website Connector | Tool to ingest website content via sitemap URL in AI21 Studio. Use when you need to process and index website pages from a sitemap for RAG, grounding, or document analysis purposes. |
| `STUDIO_BY_AI21_LABS_INGEST_WEBSITE_CONNECTOR_URL` | Ingest Website Connector URL | Tool to ingest a website URL into AI21 Studio's website connector. Use when you need to add a specific URL to be processed and indexed by the website connector for RAG or grounding. |
| `STUDIO_BY_AI21_LABS_LIST_ASSISTANTS` | List Assistants | Tool to retrieve all assistants from AI21 Studio. Use when you need to list available assistants, optionally filtered by workspace IDs. |
| `STUDIO_BY_AI21_LABS_LIST_WEBSITE_CONNECTORS` | List Website Connectors | Tool to retrieve website connector information from AI21 Studio. Use when you need to get details about configured website connectors. |
| `STUDIO_BY_AI21_LABS_LIST_DEMOS` | List Demos | Tool to retrieve all demos from AI21 Studio. Use when you need to list all available demos including their names, statuses, visibility settings, and configurations. |
| `STUDIO_BY_AI21_LABS_LIST_LIBRARY_FILES` | List Library Files | Tool to list files in the workspace library with optional filtering. Use to retrieve file metadata, search by name/path/status/labels, or paginate through library contents. |
| `STUDIO_BY_AI21_LABS_LIST_MCP_STORAGE` | List MCP Storage | Tool to retrieve all MCP (Model Context Protocol) storage configurations from AI21 Studio. Use when you need to list available MCP servers and their configurations, optionally filtered by workspace ID. |
| `STUDIO_BY_AI21_LABS_LIST_MODELS` | List Models | Tool to retrieve information about all available AI21 models. Use when you need to list models with their specifications, pricing, and capabilities. |
| `STUDIO_BY_AI21_LABS_LIST_PLANS` | List Plans | Tool to list all plans for a specific assistant. Use when you need to retrieve the plans associated with an assistant ID. |
| `STUDIO_BY_AI21_LABS_LIST_SECRETS` | List Secrets | Tool to retrieve all secrets from AI21 Studio secret storage. Use when you need to list stored secrets and their metadata. |
| `STUDIO_BY_AI21_LABS_LIST_WORKSPACE_MODELS` | List Workspace Models | Tool to retrieve all workspace models by organization from AI21 Studio. Use when you need to list available models for the workspace. |
| `STUDIO_BY_AI21_LABS_LIST_AVAILABLE_MODELS` | List Available Models | Tool to retrieve all available models from AI21 Studio settings. Use when you need to list models that are available for use in the workspace. |
| `STUDIO_BY_AI21_LABS_MODIFY_ASSISTANT` | Modify Assistant | Tool to modify an existing AI21 Studio assistant. Use when you need to update assistant properties like name, description, models, system prompt, or configuration. At least one field must be provided to update. All fields except assistant_id are optional. |
| `STUDIO_BY_AI21_LABS_MODIFY_ASSISTANT_ROUTE` | Modify Assistant Route | Tool to modify an existing route within an assistant. Use when you need to update the description or examples of a specific route in an AI21 Studio assistant. |
| `STUDIO_BY_AI21_LABS_MODIFY_ASSISTANT_PLAN` | Modify Assistant Plan | Tool to modify an existing assistant plan in AI21 Studio. Use when you need to update the code or schemas of a plan. |
| `STUDIO_BY_AI21_LABS_RETRY_INGEST_WEBSITE` | Retry Ingest Website | Tool to retry ingestion of a website in AI21 Studio. Use when a website ingestion has failed and you need to trigger another attempt to ingest the content. |
| `STUDIO_BY_AI21_LABS_RUN_ASSISTANT` | Run Assistant | Tool to run an AI21 Studio assistant with conversational input. Use when you need to interact with a configured AI21 assistant by providing messages and receiving responses. The assistant processes the input messages and returns a result based on its configuration. Supports multiple languages and optional features like dynamic planning and structured RAG. |
| `STUDIO_BY_AI21_LABS_SYNC_WEBSITE_CONNECTOR` | Sync Website Connector | Tool to sync a website connector in AI21 Studio. Use when you need to trigger a synchronization of website content for a specific connector. |
| `STUDIO_BY_AI21_LABS_UPDATE_DEMO` | Update Demo | Tool to update an existing demo in Studio by AI21 Labs. Use when you need to modify demo properties such as name, status, visibility, or configuration. |
| `STUDIO_BY_AI21_LABS_UPDATE_MCP_STORAGE` | Update MCP Storage | Tool to update an existing MCP (Model Context Protocol) storage configuration in AI21 Studio. Use when you need to modify the server label of an MCP storage configuration. |
| `STUDIO_BY_AI21_LABS_UPDATE_SECRET` | Update Secret | Tool to update an existing secret in AI21 Studio. Use when you need to modify secret properties such as name or value. |
| `STUDIO_BY_AI21_LABS_VALIDATE_PLAN` | Validate Plan | Tool to validate Python code for an AI21 Studio assistant plan. Use when you need to verify that code is syntactically correct and executable before using it in an assistant. |

## Supported Triggers

None listed.

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

The Studio By Ai21 Labs MCP server is an implementation of the Model Context Protocol that connects your AI agent to Studio By Ai21 Labs. It provides structured and secure access so your agent can perform Studio By Ai21 Labs 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 Studio By Ai21 Labs account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Studio By Ai21 Labs

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 Studio By Ai21 Labs 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, studio by ai21 labs)
- 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 Studio By Ai21 Labs 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=["studio_by_ai21_labs"],
    )

    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 Studio By Ai21 Labs actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Studio By Ai21 Labs 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: ["studio_by_ai21_labs"],
    },
  );

  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 Studio By Ai21 Labs 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 Studio By Ai21 Labs
```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 Studio By Ai21 Labs, 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=["studio_by_ai21_labs"],
    )

    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 Studio By Ai21 Labs actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Studio By Ai21 Labs 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: ["studio_by_ai21_labs"],
    },
  );

  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 Studio By Ai21 Labs 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 Studio By Ai21 Labs to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Studio By Ai21 Labs 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 Studio By Ai21 Labs MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/studio_by_ai21_labs/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/studio_by_ai21_labs/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/studio_by_ai21_labs/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/studio_by_ai21_labs/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/studio_by_ai21_labs/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/studio_by_ai21_labs/framework/cli)
- [Google ADK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/studio_by_ai21_labs/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/studio_by_ai21_labs/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/studio_by_ai21_labs/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/studio_by_ai21_labs/framework/crew-ai)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions.
- [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences.
- [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement.
- [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team.
- [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs.
- [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code.
- [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets.
- [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Studio By Ai21 Labs MCP?

With a standalone Studio By Ai21 Labs MCP server, the agents and LLMs can only access a fixed set of Studio By Ai21 Labs tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Studio By Ai21 Labs 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 Studio By Ai21 Labs tools.

### Can I manage the permissions and scopes for Studio By Ai21 Labs while using Tool Router?

Yes, absolutely. You can configure which Studio By Ai21 Labs 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 Studio By Ai21 Labs data and credentials are handled as safely as possible.

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