# How to integrate Finerworks MCP with LlamaIndex

```json
{
  "title": "How to integrate Finerworks MCP with LlamaIndex",
  "toolkit": "Finerworks",
  "toolkit_slug": "finerworks",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/finerworks/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/finerworks/framework/llama-index.md",
  "updated_at": "2026-05-12T10:11:30.884Z"
}
```

## Introduction

This guide walks you through connecting Finerworks to LlamaIndex using the Composio tool router. By the end, you'll have a working Finerworks agent that can add five new artwork images to your library, list all available fine art paper types, submit a print order for three photos through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Finerworks account through Composio's Finerworks MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Finerworks with

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

The Finerworks MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your FinerWorks account. It provides structured and secure access to your fine art and photo printing services, so your agent can perform actions like uploading artwork, managing orders, updating account info, and exploring product options on your behalf.
- Artwork upload and management: Easily add new images to your FinerWorks library, complete with metadata and image URIs, so your inventory is always up to date.
- Order submission and tracking: Ask your agent to submit batches of print orders or retrieve shipping options, streamlining your print fulfillment process.
- Product and media exploration: Instantly list available product types, media types, and style options to help you select the perfect materials for your artwork.
- Account and profile updates: Let your agent fetch or update your user profile, including business information, billing details, and payment profiles, as your needs change.
- Credential verification and file selection: Test your credentials for peace of mind, or update which image files are selected for current projects—all without manual steps.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `FINERWORKS_ADD_IMAGES` | Add Images | Tool to add images to a finerworks library. Use after preparing up to 5 images with metadata and URIs. |
| `FINERWORKS_ADD_UPDATE_GALLERY_COLLECTION` | Add or Update Gallery Collection | Tool to add or update personal gallery collections in GeoGalleries.com. Use when creating new collections or modifying existing ones. Omit id or set to 0 for new collections; provide existing id to update. |
| `FINERWORKS_DELETE_IMAGES` | Delete Images | Tool to delete a list of image files from FinerWorks based on their unique GUIDs. Note: If an image is assigned to the inventory library, this will also remove any virtual inventory products assigned to those images. Use when you need to permanently remove images from a library. |
| `FINERWORKS_DELETE_PENDING_ORDERS` | Delete Pending Orders | Tool to remove orders from temporary storage that were saved as pending. Use when you need to delete pending orders by their identifiers. |
| `FINERWORKS_DELETE_VIRTUAL_INVENTORY` | Delete Virtual Inventory | Tool to delete virtual inventory products by SKU. Use when removing products from virtual inventory. Note that deleted items will lose any sync connection with 3rd party platforms. |
| `FINERWORKS_DISCONNECT_VIRTUAL_INVENTORY` | Disconnect Virtual Inventory | Tool to disconnect ALL virtual inventory items from a 3rd party platform. Use when you need to remove platform data (e.g., Shopify, WooCommerce, Etsy) from all virtual inventory items. |
| `FINERWORKS_FETCH_ORDER_STATUS` | Fetch Order Status | Tool to retrieve order production status and tracking details from FinerWorks. Use when you need to check the current status of orders including shipment tracking information. |
| `FINERWORKS_GET_COMPANY_INFO` | Get Company Info | Tool to get essential information about FinerWorks including site identifier, company address, and operating hours. Use when you need to retrieve FinerWorks' contact information or business location details. |
| `FINERWORKS_GET_FRAME_DETAILS` | Get Frame Details | Tool to retrieve detailed specifications for a specific frame by ID. Returns dimensions, pricing, material info, size constraints, and URLs for visual references. Use when you need complete frame specifications for order processing or product catalog display. |
| `FINERWORKS_GET_PRICES` | Get Prices | Tool to retrieve pricing information for FinerWorks products. Use when you need to get price quotes for specific product SKUs and quantities. |
| `FINERWORKS_GET_SHIPPING_OPTIONS_IDS` | Get Shipping Options IDs | Tool to list all available shipping option IDs from FinerWorks. Use this to retrieve IDs for various shipping methods that can be used for cross-reference purposes when configuring orders. Sites should periodically check and update this data in case new shipping methods are added or deleted. |
| `FINERWORKS_GET_USER` | Get User | Retrieves the authenticated user's FinerWorks account profile including billing/business addresses, account credits, shipping preferences, connected platforms, and gallery settings. Use this to get user details like account_key, email, credits balance, or to verify authentication. |
| `FINERWORKS_LIST_FILE_SELECTION` | List File Selection | Tool to retrieve the list of currently selected files by their master guid. Use when you need to see which file GUIDs are grouped under a specific selection key. |
| `FINERWORKS_LIST_FRAME_COLLECTIONS` | List Frame Collections | Retrieve available frame collections and categories from FinerWorks. Use this to discover frame options for print orders. Pass a collection ID to get detailed frame specifications within that collection, or filter by product code to see only compatible frames. Returns all collections if no filters specified. |
| `FINERWORKS_LIST_GALLERIES` | List Galleries | Tool to list galleries setup in GeoGalleries.com for the user's account. Use when you need to retrieve available galleries, filter by personal galleries, or get specific galleries by their IDs. |
| `FINERWORKS_LIST_GALLERY_THEMES` | List Gallery Themes | Tool to retrieve available themes for GeoGalleries. Use when you need to discover valid theme options for gallery customization or when filtering galleries by theme. |
| `FINERWORKS_LIST_GLAZING` | List Glazing | Retrieve available glazing and glass options from FinerWorks. Use this to discover glazing choices (UV protection glass, acrylic, etc.) for framed prints. Call without parameters to list all glazing options, or pass a specific ID to filter results. |
| `FINERWORKS_LIST_IMAGES` | List Images | Tool to retrieve a paginated list of image files uploaded to your FinerWorks account. Use this to browse your image inventory, search by filters, or get specific images by GUID. Supports pagination, sorting, date filtering, and gallery filtering. |
| `FINERWORKS_LIST_MATS` | List Mats | Retrieve available matting options from FinerWorks for framing products. Mats include specifications like dimensions, colors, thickness, and pricing. Use this to discover valid mat IDs and specifications before configuring framed prints. |
| `FINERWORKS_LIST_MEDIA_TYPES` | List Media Types | Retrieve available print media types from FinerWorks. Media types represent printing substrates (e.g., canvas, paper, vinyl) and include associated product type and style information. Call without parameters to list all media types, or pass specific IDs to filter results. |
| `FINERWORKS_LIST_ORDER_STATUS_DEFINITIONS` | List Order Status Definitions | Tool to list all available production status definitions an order can have once it has completed. Use the order_status_id for reference purposes since the descriptive label can be redundant or change wording in some cases. |
| `FINERWORKS_LIST_PRODUCT_TYPES` | List Product Types | Retrieve FinerWorks product types (print categories like Canvas Prints, Metal Prints, Posters, etc.). Use this to discover available printing options and their media IDs before placing orders. Returns all product types if no IDs specified, or filtered results for specific IDs. |
| `FINERWORKS_LIST_SHIPPING_OPTIONS_MULTIPLE` | List Shipping Options Multiple | Retrieve shipping options and rates for multiple orders in a batch request. Use this tool to get available shipping methods, rates, and estimated delivery times before submitting orders. Returns all available shipping options for each order with pricing breakdown including shipping rate, taxes, and total cost. The returned shipping_code values (e.g., 'FL', 'GD', '2A') should be used when submitting the actual order via submit_orders. Supports both US domestic and international shipping destinations. |
| `FINERWORKS_LIST_STYLE_TYPES` | List Style Types | Retrieves available print style types from FinerWorks. Style types define how prints are formatted (e.g., border sizes, canvas wraps, panel depths). Use this to discover valid style_type_id values needed when creating print orders or configuring products. Each style type includes sizing constraints, framing options, and border/bleed specifications. |
| `FINERWORKS_LIST_VIRTUAL_INVENTORY` | List Virtual Inventory | Tool to retrieve a user's virtual inventory products from their FinerWorks account. Use when you need to list products with valid product codes, search by SKU or product code, or filter by creation date. Returns paginated results with product details including pricing, images, and stock information. |
| `FINERWORKS_SAVE_PENDING_ORDERS` | Save Pending Orders | Tool to save orders to temporary pending storage. Use when orders need review or modification before final submission. |
| `FINERWORKS_SUBMIT_ORDERS` | Submit Orders | Tool to submit up to five new orders. Use after all customer and line-item details are finalized. |
| `FINERWORKS_UPDATE_APP_DETAILS` | Update App Details | Tool to update the details assigned to the app_key being used. Use when you need to modify app name, description, miscellaneous data, or live mode status. |
| `FINERWORKS_UPDATE_FILE_SELECTION` | Update File Selection | Tool to update a user's currently selected image files using the selection key. Use when you need to replace the current set of files associated with a selection GUID after authentication. |
| `FINERWORKS_UPDATE_IMAGES` | Update Images | Tool to update image metadata in FinerWorks based on unique GUIDs. Use when you need to modify image properties like title, description, visibility, or gallery assignments. Note: if the image is assigned to the inventory library, this will also remove any virtual inventory products assigned to those images. |
| `FINERWORKS_UPDATE_USER` | Update User | Tool to update various features of a user's account profile. Use when you need to modify billing/business info, logos, or payment profile after retrieving current account. |
| `FINERWORKS_UPDATE_VIRTUAL_INVENTORY` | Update Virtual Inventory | Tool to update virtual inventory items within a user's account. Use when you need to modify product details like pricing, stock quantities, descriptions, or third-party integrations for existing inventory items. |
| `FINERWORKS_VALIDATE_RECIPIENT_ADDRESS` | Validate Recipient Address | Tool to validate and test a recipient address before submitting an order to ensure delivery accuracy. Use this to verify address correctness and get standardized formatting from the shipping carrier's validation service. |

## Supported Triggers

None listed.

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

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

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

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 Finerworks 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, finerworks)
- 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 Finerworks 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=["finerworks"],
    )

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

  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 Finerworks 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 Finerworks
```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 Finerworks, 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=["finerworks"],
    )

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

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

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

## Related Toolkits

- [Addresszen](https://composio.dev/toolkits/addresszen) - Addresszen is a real-time address autocomplete and verification service. It helps capture accurate, deliverable addresses with instant suggestions and validation.
- [Asin data api](https://composio.dev/toolkits/asin_data_api) - Asin data api gives you detailed, real-time product data from Amazon, including price, rank, and reviews. Perfect for e-commerce pros and data-driven marketers who need instant marketplace insights.
- [Baselinker](https://composio.dev/toolkits/baselinker) - BaseLinker is an all-in-one e-commerce management platform connecting stores, marketplaces, carriers, and more. It streamlines order processing, inventory control, and automates your sales operations.
- [Bestbuy](https://composio.dev/toolkits/bestbuy) - Best Buy is a leading retailer offering APIs for product, store, and recommendation data. Instantly access up-to-date retail insights for smarter shopping and decision-making.
- [Btcpay server](https://composio.dev/toolkits/btcpay_server) - BTCPay Server is a free, open-source, self-hosted Bitcoin payment processor. It lets merchants accept Bitcoin payments directly, cutting out middlemen and boosting privacy.
- [Cdr platform](https://composio.dev/toolkits/cdr_platform) - Cdr platform is an API for purchasing carbon dioxide removal services. It enables businesses to offset emissions by accessing verified carbon removal projects.
- [Cloudcart](https://composio.dev/toolkits/cloudcart) - CloudCart is an e-commerce platform for building and managing online stores. It helps businesses streamline product listings, orders, and customer engagement.
- [Countdown api](https://composio.dev/toolkits/countdown_api) - Countdown API gives you real-time, structured eBay product data, reviews, and seller feedback. Perfect for powering price monitoring, product research, or marketplace analytics workflows.
- [Dpd2](https://composio.dev/toolkits/dpd2) - Dpd2 is a robust email management platform for handling, sorting, and automating email workflows. Streamline your communications and boost productivity with advanced sorting, labeling, and response tools.
- [Fingertip](https://composio.dev/toolkits/fingertip) - Fingertip is a business management platform for selling, booking, and customer engagement—all from a single link. It helps businesses streamline operations and connect with customers across social channels.
- [Fraudlabs pro](https://composio.dev/toolkits/fraudlabs_pro) - FraudLabs Pro is an online payment fraud detection service for e-commerce and merchants. It helps minimize chargebacks and revenue loss by detecting and preventing fraudulent transactions.
- [Gift up](https://composio.dev/toolkits/gift_up) - Gift Up! is a digital platform for selling, managing, and redeeming gift cards online. It streamlines promotions and gift card transactions for businesses and their customers.
- [Goody](https://composio.dev/toolkits/goody) - Goody is a gifting platform that lets users send gifts and physical products without handling logistics. It streamlines gifting by managing delivery, fulfillment, and recipient experience.
- [Gumroad](https://composio.dev/toolkits/gumroad) - Gumroad is a platform for selling digital products, physical goods, and memberships with a simple checkout and marketing tools. It streamlines creator payouts and helps you grow your audience effortlessly.
- [Instacart](https://composio.dev/toolkits/instacart) - Instacart is an online grocery delivery and pickup service platform. It lets you discover local retailers and create shoppable lists and recipes with ease.
- [Junglescout](https://composio.dev/toolkits/junglescout) - Junglescout is an Amazon product research and analytics platform for sellers. It delivers sales estimates, competitive insights, and optimization tools to boost your Amazon business.
- [Ko fi](https://composio.dev/toolkits/ko_fi) - Ko-fi is a platform that lets creators receive donations, memberships, and sales from fans. It helps creators monetize their work and grow their audience with minimal friction.
- [Lemon squeezy](https://composio.dev/toolkits/lemon_squeezy) - Lemon Squeezy is a payments and subscription platform built for software companies. It makes managing payments, taxes, and customer subscriptions effortless.
- [Loyverse](https://composio.dev/toolkits/loyverse) - Loyverse is a point-of-sale (POS) platform for small businesses, offering tools for sales, inventory, and customer loyalty. It helps streamline retail operations and boost customer engagement.
- [Memberstack](https://composio.dev/toolkits/memberstack) - Memberstack lets you add user authentication, payments, and member management to your website—no backend code required. Easily manage your site's members and subscriptions from a single platform.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Finerworks MCP?

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

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

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

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