# How to integrate Dovetail MCP with LlamaIndex

```json
{
  "title": "How to integrate Dovetail MCP with LlamaIndex",
  "toolkit": "Dovetail",
  "toolkit_slug": "dovetail",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/dovetail/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/dovetail/framework/llama-index.md",
  "updated_at": "2026-05-12T10:09:39.806Z"
}
```

## Introduction

This guide walks you through connecting Dovetail to LlamaIndex using the Composio tool router. By the end, you'll have a working Dovetail agent that can summarize all data points for project x, create a new insight from interview notes, list every contact added this month through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Dovetail account through Composio's Dovetail MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Dovetail with

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

The Dovetail MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Dovetail account. It provides structured and secure access to your research workspace, so your agent can perform actions like creating insights, managing contacts, organizing channels, and retrieving research notes on your behalf.
- Automated insight creation: Let your agent synthesize findings and store new insights in your Dovetail projects, streamlining your research analysis workflow.
- Channel and topic management: Easily create, organize, or delete channels and topics to keep your research data structured and accessible.
- Contact management and retrieval: Automatically add new research contacts or list all contacts in your workspace for better respondent tracking.
- Research note access: Ask your agent to fetch detailed information about specific notes, giving you instant access to key research materials.
- Data point recording and classification: Capture and categorize new data points within channels, ensuring every piece of feedback or observation is logged and ready for analysis.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `DOVETAIL_CREATE_CHANNEL` | Create Channel | Creates a new channel in Dovetail to organize and collect feedback data. Channels are containers for specific types of customer feedback such as app reviews, NPS responses, churn reasons, product reviews, or support tickets. Use this to set up a new data collection source before importing feedback data. |
| `DOVETAIL_CREATE_CONTACT` | Create Contact | Tool to create a new contact in Dovetail. Use when you need to register a contact before logging interactions. |
| `DOVETAIL_CREATE_DATA` | Create Data | Tool to create a data item in a Dovetail project with text content, title, and/or structured fields. Use when you need to capture and store research data, interview notes, or other content in a project. |
| `DOVETAIL_CREATE_DATA_POINT` | Create Data Point | Tool to create a data point within a channel. Use after capturing new content to record and classify it in Dovetail. |
| `DOVETAIL_CREATE_DOC` | Create Doc | Tool to create a doc in a Dovetail project with text content, title and/or custom fields. Use when you need to document research findings, store notes, or create structured content within a project. The doc content is stored but not returned in the response. |
| `DOVETAIL_CREATE_INSIGHT` | Create Insight | Creates a new insight in Dovetail to store synthesized research findings, observations, or conclusions. Use this tool when you need to document and save key findings from user research, interviews, or data analysis. Insights can optionally be linked to a project for better organization. Returns the created insight's ID, title, creation timestamp, and other metadata. Note: The body content is stored but not included in the response. |
| `DOVETAIL_CREATE_NOTE` | Create Note | Tool to create a note in a Dovetail project with text content, title and/or custom fields. Use when you need to document research notes, store interview findings, or create structured content within a project. The note content is stored but not returned in the response. |
| `DOVETAIL_CREATE_PROJECT` | Create Project | Tool to create a new project in your Dovetail workspace. Use when you need to create a project to organize research data. |
| `DOVETAIL_CREATE_TOPIC` | Create Topic | Tool to create a new topic in a Dovetail channel. Requires channel_id, title, and description. Use to organize feedback within channels by creating themed discussion topics. |
| `DOVETAIL_DELETE_CHANNEL` | Delete Channel | Tool to delete an existing channel. Use when you need to remove a channel and move it to the project's trash (restorable for 30 days). Confirm the channel ID before calling. |
| `DOVETAIL_DELETE_DATA` | Delete Data | Tool to delete an existing data item. Use when you have confirmed the data ID and want to move it to trash (restorable for 30 days). Example: "Delete data with ID 1tFfvvAmYPCLUqb9zO8dgN." |
| `DOVETAIL_DELETE_DOC` | Delete Doc | Tool to delete an existing doc. Use when you need to remove a doc and move it to the project's trash (restorable for 30 days). |
| `DOVETAIL_DELETE_INSIGHT` | Delete Insight | Tool to delete an existing insight. Use when you have confirmed the insight ID and want to move it to trash (restorable for 30 days). |
| `DOVETAIL_DELETE_NOTE` | Delete Note | Tool to delete an existing note. Use when you have confirmed the note ID and want to move it to trash (restorable for 30 days). |
| `DOVETAIL_DELETE_TOPIC` | Delete Topic | Tool to delete an existing topic. Use when you have confirmed the topic ID and want to move it to trash (restorable for 30 days). Example: "Delete topic with ID 123e4567-e89b-12d3-a456-426614174000." |
| `DOVETAIL_EXPORT_DATA` | Export Data | Tool to export data in HTML or Markdown format. Use when you need to retrieve a formatted version of data items from Dovetail. |
| `DOVETAIL_EXPORT_DOC` | Export Doc | Tool to export a doc in HTML or Markdown format. Use when you need to retrieve the full content of a doc from Dovetail in a specific format. |
| `DOVETAIL_EXPORT_INSIGHT` | Export Insight | Tool to export an insight in HTML or Markdown format. Use when you need to retrieve the full content of an insight for documentation, reporting, or sharing purposes. The exported content includes the insight's title and body in the specified format. |
| `DOVETAIL_EXPORT_NOTE` | Export Note | Tool to export a note from Dovetail in HTML or Markdown format. Use when you need to retrieve the full content of a note in a specific export format. |
| `DOVETAIL_GET_CONTACT` | Get Contact | Tool to retrieve details of a specific contact. Use when you have confirmed the contact ID and need full contact metadata from Dovetail. |
| `DOVETAIL_GET_DATA` | Get Data | Tool to retrieve details of a specific data item by ID. Use when you have confirmed the data ID and need full metadata including custom fields, files, and project information from Dovetail. |
| `DOVETAIL_GET_DOC` | Get Doc | Tool to retrieve details of a specific doc by ID. Use when you have confirmed the doc ID and need full doc metadata from Dovetail. |
| `DOVETAIL_GET_FILE` | Get File | Tool to retrieve details of a specific file by its ID. Use when you need file metadata, download URL, or processing status from Dovetail. |
| `DOVETAIL_GET_FOLDER` | Get Folder | Tool to retrieve details of a specific folder. Use when you have confirmed the folder ID and need full folder metadata from Dovetail. |
| `DOVETAIL_GET_INSIGHT` | Get Insight | Tool to retrieve details of a specific insight by ID. Use when you need full insight metadata from Dovetail. |
| `DOVETAIL_GET_NOTE` | Get Note | Tool to retrieve details of a specific note. Use when you have confirmed the note ID and need full note metadata from Dovetail. |
| `DOVETAIL_GET_PROJECT` | Get Project | Tool to retrieve details of a specific project. Use when you have confirmed the project ID and need full project metadata from Dovetail. |
| `DOVETAIL_GET_TOKEN_INFO` | Get Token Info | Retrieves information about the current API token, including its unique identifier and the associated workspace subdomain. Use this to verify which workspace the token belongs to. |
| `DOVETAIL_IMPORT_DATA_FILE` | Import Data File | Tool to import a public URL of a file as new data in Dovetail. Use when you need to add external files to a project. |
| `DOVETAIL_IMPORT_DOC_FILE` | Import Doc File | Tool to import a public file URL as a new doc in Dovetail. Use when you need to create a doc from an external file source. The file must be publicly accessible at the provided URL. |
| `DOVETAIL_IMPORT_INSIGHT_FILE` | Import Insight from File | Tool to import a file from a public URL as a new insight in Dovetail. Use when you need to create an insight from an external file source such as PDFs, images, or documents. The file must be publicly accessible for Dovetail to fetch and import it. After import, the insight can be analyzed, tagged, and connected to projects. |
| `DOVETAIL_IMPORT_NOTE_FILE` | Import Note File | Tool to import a file from a public URL as a new note in Dovetail. Use when you need to create a note by importing content from an accessible file URL (PDF, video, audio, etc.). |
| `DOVETAIL_LIST_CONTACTS` | List Contacts | Retrieves a paginated list of contacts from a Dovetail workspace. Returns contact IDs, names, creation timestamps, and custom fields. Use cursor-based pagination (limit + start_cursor) to navigate large contact lists efficiently. |
| `DOVETAIL_LIST_DATA` | List Data | Tool to list data items in Dovetail. Use when you need to retrieve, filter, sort, or paginate through your workspace data. Supports filtering by created_at (date range), project_id, and title. Results can be sorted by created_at or title. Uses cursor-based pagination with configurable page size. |
| `DOVETAIL_LIST_DOCS` | List Docs | Tool to list docs in a Dovetail workspace with optional filtering, sorting, and pagination. Use when you need to retrieve docs, optionally filtered by project, title, content, or creation date. |
| `DOVETAIL_LIST_FOLDERS` | List Folders | Tool to get a list of folders associated with a workspace. Use when you need to retrieve folder hierarchy, search for folders by title, or navigate the folder structure with pagination support. |
| `DOVETAIL_LIST_HIGHLIGHTS` | List Highlights | List highlights from your Dovetail workspace with optional filtering and pagination. Use this action to retrieve highlights that have been created across your notes and projects. Supports filtering by project or note, and cursor-based pagination for large result sets. |
| `DOVETAIL_LIST_INSIGHTS` | List Insights | Tool to get a list of insights associated with a workspace. Use when you need to retrieve insights with optional filtering by project, publication status, or title, and support for cursor-based pagination. |
| `DOVETAIL_LIST_NOTES` | List Notes | List notes in Dovetail workspace with optional pagination and sorting. Use this tool to retrieve notes from your Dovetail workspace. Supports pagination for large result sets and sorting options. Returns note metadata including IDs, titles, timestamps, and associated project information. |
| `DOVETAIL_LIST_PROJECTS` | List Projects | Tool to list all projects in Dovetail. Use after authenticating with a valid workspace token when you need to retrieve the full project list. |
| `DOVETAIL_LIST_TAGS` | List Tags | List all tags in the authenticated Dovetail workspace. Returns tag details including title, color, highlight count, and timestamps. Supports pagination for workspaces with many tags. |
| `DOVETAIL_LIST_USER_DOCS` | List User Docs | Tool to get a list of docs associated with a user in Dovetail. Use when you need to retrieve documents for a specific user or the authenticated user (use 'me' as user_id). |
| `DOVETAIL_LIST_USER_INSIGHTS` | List User Insights | List personal insights for a user in Dovetail. Returns a paginated list of insights including their IDs, titles, creation dates, and published status. Use DOVETAIL_GET_TOKEN_INFO to obtain a valid user_id. |
| `DOVETAIL_MAGIC_SEARCH` | Magic Search | Tool to perform a magic search across workspace data. Use when you need to retrieve relevant highlights, notes, insights, channels, themes, or tags by query. |
| `DOVETAIL_UPDATE_CHANNEL` | Update Channel | Tool to update an existing channel's title or context. Use after confirming the channel ID and fields to change. |
| `DOVETAIL_UPDATE_CONTACT` | Update Contact | Tool to update an existing contact in Dovetail. Use when you need to modify a contact's name, email, or custom fields. |
| `DOVETAIL_UPDATE_DATA` | Update Data | Tool to update a data item in Dovetail. Use when you need to modify the title or fields of an existing data item. |
| `DOVETAIL_UPDATE_DOC` | Update Doc | Tool to update a doc in Dovetail. Use when you need to modify a doc's title or custom fields. |
| `DOVETAIL_UPDATE_INSIGHT` | Update Insight | Updates an existing insight in Dovetail, allowing you to modify the title and custom fields. Use when you need to revise insight information, correct titles, or update custom field values. |
| `DOVETAIL_UPDATE_NOTE` | Update Note | Tool to update an existing note in Dovetail. Use when you need to modify a note's title, content, or custom fields. Example: "Update note 8IFq5LEC6hV1Vgsu0jPNJ with new title 'Q1 Review'". |
| `DOVETAIL_UPDATE_TOPIC` | Update Topic | Tool to update an existing topic. Use after confirming the topic ID and fields to change. Example: "Update topic with id 123... to have title 'New'". |

## Supported Triggers

None listed.

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

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

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

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 Dovetail 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, dovetail)
- 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 Dovetail 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=["dovetail"],
    )

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

  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 Dovetail 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 Dovetail
```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 Dovetail, 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=["dovetail"],
    )

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

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

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

## Related Toolkits

- [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.
- [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.
- [Exa](https://composio.dev/toolkits/exa) - Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows.
- [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.
- [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data.
- [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds.
- [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights.
- [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly.
- [Bright Data MCP](https://composio.dev/toolkits/brightdata_mcp) - Bright Data MCP is an AI-powered web scraping and data collection platform. Instantly access public web data in real time with advanced scraping tools.
- [Browseai](https://composio.dev/toolkits/browseai) - Browseai is a web automation and data extraction platform that turns any website into an API. It's perfect for monitoring websites and retrieving structured data without manual scraping.
- [ClickHouse](https://composio.dev/toolkits/clickhouse) - ClickHouse is an open-source, column-oriented database for real-time analytics and big data processing using SQL. Its lightning-fast query performance makes it ideal for handling large datasets and delivering instant insights.
- [Coinmarketcal](https://composio.dev/toolkits/coinmarketcal) - CoinMarketCal is a community-powered crypto calendar for upcoming events, announcements, and releases. It helps traders track market-moving developments and stay ahead in the crypto space.
- [Control d](https://composio.dev/toolkits/control_d) - Control d is a customizable DNS filtering and traffic redirection platform. It helps you manage internet access, enforce policies, and monitor usage across devices and networks.
- [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.
- [Databricks](https://composio.dev/toolkits/databricks) - Databricks is a unified analytics platform for big data and AI on the lakehouse architecture. It empowers data teams to collaborate, analyze, and build scalable solutions efficiently.
- [Datagma](https://composio.dev/toolkits/datagma) - Datagma delivers data intelligence and analytics for business growth and market discovery. Get actionable market insights and track competitors to inform your strategy.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Dub](https://composio.dev/toolkits/dub) - Dub is a short link management platform with analytics and API access. Use it to easily create, manage, and track branded short links for your business.
- [Elasticsearch](https://composio.dev/toolkits/elasticsearch) - Elasticsearch is a distributed, RESTful search and analytics engine for all types of data. It delivers fast, scalable search and powerful analytics across massive datasets.
- [Fireflies](https://composio.dev/toolkits/fireflies) - Fireflies.ai is an AI-powered meeting assistant that records, transcribes, and analyzes voice conversations. It helps teams capture call notes automatically and search or summarize meetings effortlessly.

## Frequently Asked Questions

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

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

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

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

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