# How to integrate Jigsawstack MCP with LlamaIndex

```json
{
  "title": "How to integrate Jigsawstack MCP with LlamaIndex",
  "toolkit": "Jigsawstack",
  "toolkit_slug": "jigsawstack",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/jigsawstack/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/jigsawstack/framework/llama-index.md",
  "updated_at": "2026-05-12T10:16:25.125Z"
}
```

## Introduction

This guide walks you through connecting Jigsawstack to LlamaIndex using the Composio tool router. By the end, you'll have a working Jigsawstack agent that can generate a logo from this business idea, analyze customer review sentiment for this product, convert this sales script into an audio file through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Jigsawstack account through Composio's Jigsawstack MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Jigsawstack with

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

The Jigsawstack MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Jigsawstack account. It provides structured and secure access to Jigsawstack's suite of custom AI models, so your agent can perform actions like generating images, analyzing sentiment, converting text to speech, and running smart web searches on your behalf.
- AI-powered image generation: Instantly create custom images from any text prompt, perfect for visual content, ideation, or creative tasks.
- Text sentiment analysis: Have your agent classify the emotional tone of written content, detecting positive, negative, or neutral sentiment for feedback, moderation, or analytics.
- Natural text-to-speech synthesis: Convert any text into clear, natural-sounding audio files, enabling voice experiences or accessibility features in your workflows.
- Enhanced web search with AI summaries: Perform smart, geo-aware web searches and get concise, AI-generated overviews for quick research and information gathering.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `JIGSAWSTACK_CHECK_NSFW` | Check Image for NSFW Content | Tool to detect NSFW content in images. Use when you need to quickly detect nudity, violence, hentai, porn and other NSFW content in images. |
| `JIGSAWSTACK_CHECK_PROFANITY` | Check Profanity | Tool to check text for profanity and inappropriate language. Use when you need to validate user-generated content, filter inappropriate language, or sanitize text input. |
| `JIGSAWSTACK_CHECK_SPAM` | Check Spam | Tool to perform spam check analysis on text. Use when you need to detect spam content and get a spam confidence score. |
| `JIGSAWSTACK_CHECK_SPELLING` | Check Spelling | Tool to check and correct spelling errors in text. Use when you need to validate text for spelling mistakes and get correction suggestions. |
| `JIGSAWSTACK_CLASSIFY_CONTENT` | Classify Content | Tool to classify text and image datasets using custom labels. Use when you need to categorize content into predefined labels. |
| `JIGSAWSTACK_CONVERT_HTML_TO_ANY` | Convert HTML to Image or PDF | Tool to convert HTML to images (PNG/JPEG/WEBP) or PDF, or capture website screenshots. Use when you need to generate visual representations of HTML content or web pages. |
| `JIGSAWSTACK_CREATE_EMBEDDING_V2` | Create Embedding V2 | Tool to generate enhanced vector embeddings with speaker fingerprint support using the v2 model. Use when you need to create embeddings from text, images, audio, or PDF files. |
| `JIGSAWSTACK_CREATE_PREDICTION` | Create Prediction | Tool to forecast time series data using AI-powered prediction. Use when you need to predict future values based on historical data patterns. |
| `JIGSAWSTACK_CREATE_PROMPT` | Create Prompt | Tool to create a new prompt in the Prompt Engine for reusable LLM interactions. Use when you need to store and manage prompt templates with variable inputs. |
| `JIGSAWSTACK_CREATE_VOICE_CLONE` | Create Voice Clone | Tool to create a cloned voice for text-to-speech synthesis. Use when you need to clone a voice from an audio sample for later use in TTS operations. |
| `JIGSAWSTACK_DETECT_OBJECTS` | Detect Objects in Image | Tool to recognize and identify objects within an image using computer vision AI. Use when you need to detect and locate objects in images. |
| `JIGSAWSTACK_EXTRACT_VOCR` | Extract Data with Vision OCR | Tool to recognize, describe and retrieve data within images with great accuracy using Vision OCR. Use when you need to extract text, data fields, or descriptions from images or PDFs. |
| `JIGSAWSTACK_GET_SEARCH_SUGGESTIONS` | Get Search Suggestions | Tool to get real-time search suggestions for a given query. Use when you need to provide autocomplete suggestions or related search queries. |
| `JIGSAWSTACK_GET_SENTIMENT` | Get Sentiment | Tool to retrieve sentiment analysis via GET request. Use when you need to classify text into positive, negative, or neutral sentiment using a GET endpoint. |
| `JIGSAWSTACK_IMAGE_GENERATION` | Generate Image from Prompt | Tool to generate images from text prompts. Use when you need visual content created from a prompt. |
| `JIGSAWSTACK_LIST_PROMPTS` | List Prompts | Tool to list all prompts stored in the Prompt Engine. Use when you need to retrieve or view stored prompts. |
| `JIGSAWSTACK_RUN_PROMPT_BY_ID` | Run Prompt By ID | Tool to execute a stored prompt using its prompt engine ID. Use when you need to run a pre-configured prompt template with dynamic input values. |
| `JIGSAWSTACK_SCRAPE_WEBSITE` | Scrape Website | Tool to scrape any website and extract structured data using AI-powered element prompts or CSS selectors. Use when you need to extract specific information from web pages without writing custom scraping code. Supports both URL-based scraping and direct HTML content parsing. |
| `JIGSAWSTACK_SENTIMENT_ANALYSIS` | Sentiment Analysis | Tool to analyze text sentiment. Use when you need to classify text into positive, negative, or neutral sentiment. |
| `JIGSAWSTACK_SUMMARIZE_TEXT` | Summarize Text | Tool to generate concise, intelligent summaries of text or documents with AI. Use when you need to condense long content into bullet points or paragraphs. |
| `JIGSAWSTACK_TEXT_TO_SPEECH` | Text to Speech | Tool to convert text to natural-sounding speech. Use when you need to generate an audio file from text input. |
| `JIGSAWSTACK_TRANSLATE_TEXT` | Translate Text | Tool to translate text from one language to another. Use when you need to convert text between different languages with automatic language detection support. |
| `JIGSAWSTACK_WEB_SEARCH` | Web Search | Tool to perform AI-powered web search with AI overview and geo-aware results. Use when you need concise search results enriched with AI summary and location context. |

## Supported Triggers

None listed.

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

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

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

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 Jigsawstack 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, jigsawstack)
- 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 Jigsawstack 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=["jigsawstack"],
    )

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

  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 Jigsawstack 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 Jigsawstack
```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 Jigsawstack, 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=["jigsawstack"],
    )

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

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

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

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

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

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

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