# How to integrate Conveyor MCP with LlamaIndex

```json
{
  "title": "How to integrate Conveyor MCP with LlamaIndex",
  "toolkit": "Conveyor",
  "toolkit_slug": "conveyor",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/conveyor/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/conveyor/framework/llama-index.md",
  "updated_at": "2026-09-24T11:02:20.757Z"
}
```

## Introduction

This guide walks you through connecting Conveyor to LlamaIndex using the Composio tool router. By the end, you'll have a working Conveyor agent that can list all pending authorization requests, fetch all documents in your trust center, delete a folder by its id through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Conveyor account through Composio's Conveyor MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Conveyor with

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

## 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 Conveyor
- Connect LlamaIndex to the Conveyor MCP server
- Build a Conveyor-powered agent using LlamaIndex
- Interact with Conveyor 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 Conveyor MCP server, and what's possible with it?

The Conveyor MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Conveyor account. It provides structured and secure access to your security reviews and compliance workflows, so your agent can perform actions like retrieving documents, managing authorization requests, tracking connections, and automating security questionnaire processes on your behalf.
- Authorization request management: Fetch, list, and review details of all authorization requests, making it easy for your agent to help you track and respond to security and compliance requests in real time.
- Document and folder automation: Retrieve, organize, or delete specific documents and folders, ensuring your Trust Center stays tidy and up to date without manual effort.
- Connection insights and tracking: Access a complete list of your Conveyor connections, letting your agent monitor integrations and stay on top of your security ecosystem.
- Interaction history by document: Instantly pull all interactions related to a specific document, so your agent can summarize or audit user activity for compliance needs.
- API token validation and guidance: Use AI-driven guidance to validate API tokens and get structured support for access issues, helping keep your Conveyor integration secure and running smoothly.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CONVEYOR_DELETE_DOCUMENT` | Delete a Conveyor document | Tool to delete a specific document. Use when you need to remove a document by its ID. |
| `CONVEYOR_DELETE_FOLDER` | Delete folder | Permanently deletes a folder from the Conveyor Exchange by its UUID. Use GET_FOLDERS first to retrieve the folder_id. This action is irreversible. |
| `CONVEYOR_GET_ACCESS_GROUPS` | Get all access groups | Tool to retrieve all access groups for a program. Use when you need to fetch the complete list of access groups configured in the Conveyor Exchange. |
| `CONVEYOR_GET_AUTHORIZATION_REQUEST` | Get Authorization Request | Retrieves details of a specific authorization request from Conveyor Exchange by its ID. Use this to get information about a pending or processed access request, including the requestor's email, message, status, and associated dataroom. |
| `CONVEYOR_GET_AUTHORIZATION_REQUESTS` | Get Authorization Requests | Retrieves authorization requests from Conveyor's Trust Center. Use this tool to: - List all authorization requests (no filters) - Get pending requests awaiting approval (status='requested') - Filter by specific status ('initial', 'requested', 'approved', 'ignored') - Filter by requester email address Returns a list of authorization requests with details including requester email, status, timestamps, and optional CRM links. |
| `CONVEYOR_GET_AUTHORIZATIONS` | Get authorizations | Retrieve authorizations from your Conveyor Trust Center. Authorizations control who has access to view documents. Use this to list all authorizations or filter by status ('gated', 'authorized', 'revoked') or email address. Requires a valid API token for authentication. |
| `CONVEYOR_GET_CONNECTIONS` | Get all Conveyor connections | Tool to retrieve all connections. Use when you need to fetch the complete list of your Conveyor connections. Use after authenticating with a valid API key. |
| `CONVEYOR_GET_DOCUMENTS` | Get all Conveyor documents | Retrieves all documents from the Conveyor trust center. Returns a list of documents with their metadata including name, description, access level, versions, and timestamps. No parameters required - simply call to get all documents. |
| `CONVEYOR_GET_FOLDERS` | List all Exchange folders | Retrieves all folders from the Conveyor Exchange workspace. Returns a list of folders with their IDs, names, timestamps, and associated document IDs. Use this to discover available folders before uploading documents or managing folder contents. |
| `CONVEYOR_GET_INTERACTIONS` | Get all interactions | Tool to get all interactions (document interactions, q&a interactions) with optional filters. Use when you need to retrieve and filter interactions across all documents and Q&A sessions. |
| `CONVEYOR_GET_INTERACTIONS_BY_CONNECTION_ID` | Get interactions by connection ID | Tool to fetch interactions associated with a specific connection. Use when you need to list all interactions for a given connection after validating its existence. |
| `CONVEYOR_GET_INTERACTIONS_BY_DOCUMENT_ID` | Get interactions by document ID | Tool to fetch interactions associated with a specific document. Use when you need to list all interactions for a given document after validating its existence. |
| `CONVEYOR_GET_KNOWLEDGE_BASE_QUESTIONS` | Get Knowledge Base Questions | Retrieves knowledge base questions from Conveyor. Use to list, search, or paginate through Q&A entries stored in the knowledge base for compliance and security questionnaires. |
| `CONVEYOR_GET_PRODUCT_LINES` | Get product lines | Retrieves all product lines configured in Conveyor. Use this action to list available product lines for organizing trust documentation, authorizations, and security reviews by business segment. This is a read-only operation that requires a valid API token. Returns a list of product lines with their IDs, names, and descriptions. The list may be empty if no product lines have been configured. |
| `CONVEYOR_GET_QUESTIONNAIRES` | Get questionnaires | Retrieves all questionnaires from Conveyor with optional filters. Use this to list questionnaires by status, product line, or date ranges. Returns questionnaire metadata including assignee, connection, product lines, and completion status. |
| `CONVEYOR_PATCH_AUTHORIZATION` | Patch authorization | Update an existing authorization by revoking access or modifying Access Group assignments. Use this tool to: - Revoke a user's access to the Trust Center (set revoke=true) - Update which Access Groups a user belongs to (provide access_group_ids list) At least one of 'revoke' or 'access_group_ids' must be provided. |
| `CONVEYOR_PATCH_DOCUMENT` | Update Conveyor document | Update a Conveyor document's metadata. Use this to change a document's name, description, access level, folder location, or other properties. Requires the document UUID. |
| `CONVEYOR_PATCH_QUESTIONNAIRE_REQUEST` | Update questionnaire request | Tool to update a questionnaire request in Conveyor. Use this to modify an existing questionnaire request's external ID, case IDs, raw data, or source system information. |
| `CONVEYOR_POST_AUTHORIZATION` | Create new authorization | Tool to create a new authorization in Conveyor Exchange. Use this to grant access to a user by email address or by approving an existing authorization request. Provide either 'email' (to create a new authorization for that email) or 'request_id' (to approve an existing authorization request), but not both. |
| `CONVEYOR_POST_DOCUMENT` | Upload new document | Tool to upload a new document to Conveyor's Knowledge Library. Use when you need to add a file (<=100MB) for security compliance documentation. |
| `CONVEYOR_POST_FOLDER` | Create new folder | Tool to create a new folder in Conveyor Exchange. Use when you need to organize items into folders programmatically after obtaining an API key. |
| `CONVEYOR_POST_QUESTIONNAIRE` | Submit new questionnaire | Tool to submit a new questionnaire to Conveyor. Use when you need to create a security questionnaire or RFP submission with file uploads, portal links, or Salesforce integration. |
| `CONVEYOR_POST_QUESTIONNAIRE_REQUEST` | Create questionnaire request | Tool to create a new questionnaire request in Conveyor. Use when you need to submit a security questionnaire or compliance request for processing. Requires submitter_email and either external_id with raw_data OR case_ids from Salesforce. |
| `CONVEYOR_POST_REVIEW` | Create new review | Tool to create a review in Conveyor with optional references to external VM unique IDs. Use when you need to create a vendor review programmatically. |
| `CONVEYOR_POST_SINGLE_QUESTION` | Submit single question | Submit a single question to Conveyor's AI knowledge base and receive an immediate answer. Use this when responding to security questionnaires, compliance inquiries, or knowledge base queries. Returns the AI-generated answer along with confidence scoring when available. |

## Supported Triggers

None listed.

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

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

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

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 Conveyor 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, conveyor)
- 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 Conveyor 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=["conveyor"],
    )

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

  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 Conveyor 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 Conveyor
```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 Conveyor, 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=["conveyor"],
    )

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

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

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

## Related Toolkits

- [0CodeKit](https://composio.dev/toolkits/0codekit) - 0CodeKit is a utility API platform for AI, document, image, and data workflows. Use it to convert, validate, generate, store, and automate data without custom backend code.
- [Airtop](https://composio.dev/toolkits/airtop) - Airtop is a cloud browser platform for AI-powered web automation. Use it to navigate sites, extract data, and run reusable browser workflows.
- [Apify MCP](https://composio.dev/toolkits/apify_mcp) - Apify MCP is the official MCP server for Apify's web scraping and browser automation platform. Use it to run actors, collect structured web data, and automate crawling workflows.
- [Apilio](https://composio.dev/toolkits/apilio) - Apilio is a home automation platform that lets you connect and control smart devices from different brands. It helps you build flexible automations with complex conditions, schedules, and integrations.
- [Basin](https://composio.dev/toolkits/basin) - Basin is a no-code form backend for quickly setting up reliable contact forms. It lets you collect and manage form submissions without writing any server-side code.
- [Bika.ai](https://composio.dev/toolkits/bika) - Bika.ai is an AI automation database platform for managing spaces, teams, records, automations, and outgoing webhooks. It helps teams organize structured data and automate database-driven workflows in one place.
- [Botster](https://composio.dev/toolkits/botster) - Botster is a web automation service for running configurable data collection bots. Use it to collect structured web data without building and maintaining scrapers yourself.
- [Bouncer](https://composio.dev/toolkits/bouncer) - Bouncer is an email validation platform that verifies the authenticity of email addresses in real-time and batch. It helps boost deliverability and reduce bounce rates for your communications.
- [BrowserAct](https://composio.dev/toolkits/browseract) - BrowserAct is a hosted browser-automation service for running web workflows. Use it to execute repeatable browser tasks with templates, proxies, and APIs.
- [Celigo](https://composio.dev/toolkits/celigo) - Celigo is an integration platform as a service for connecting apps, data, and business workflows. It helps teams automate cross-system processes without building every integration from scratch.
- [CheckFlow](https://composio.dev/toolkits/checkflow) - CheckFlow is a workflow and checklist platform for repeatable processes, tasks, templates, teams, data sets, and automation. Use it to standardize operations, track process execution, and keep teams aligned.
- [CrewAI](https://composio.dev/toolkits/crew_ai) - CrewAI is a platform for running deployed automations and managing AMP control-plane resources. Use it to automate workflows and centrally control SaaS automation resources.
- [Cronfree Time Scheduler](https://composio.dev/toolkits/cronfree_time_scheduler) - Cronfree Time Scheduler is an API-based scheduler for recurring webhook calls. Use it to create and remove timezone-aware schedules without running cron.
- [Crowdin](https://composio.dev/toolkits/crowdin) - Crowdin is a localization management platform that streamlines translation workflows and collaboration. It helps teams centralize multilingual content, boost productivity, and automate translation processes.
- [Databox](https://composio.dev/toolkits/databox) - Databox is a business analytics platform that connects your data from any tool and device. It helps you track KPIs, build dashboards, and discover actionable insights.
- [Detrack](https://composio.dev/toolkits/detrack) - Detrack is a delivery management platform for real-time tracking and proof of delivery. It helps businesses automate notifications and keep customers updated every step of the way.
- [Dify](https://composio.dev/toolkits/dify) - Dify is a platform for running and managing published workflow apps via a Service API. Use it to execute workflows and inspect configuration and run history quickly.
- [Digital Humani](https://composio.dev/toolkits/digital_humani) - Digital Humani is a reforestation API for browsing planting projects, submitting tree requests, and tracking planted trees. It helps teams connect climate action directly to products, campaigns, and customer experiences.
- [Dnsfilter](https://composio.dev/toolkits/dnsfilter) - Dnsfilter is a cloud-based DNS security and content filtering solution. It helps organizations block online threats and manage safe internet access with ease.
- [EnforcedFlow](https://composio.dev/toolkits/enforcedflow) - EnforcedFlow is a work routing platform for advanced round-robin groups, agent criteria, availability, and email assignments. It helps teams distribute work fairly and quickly using configurable assignment rules.

## Frequently Asked Questions

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

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

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

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

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