# How to integrate Fireflies MCP with LlamaIndex

```json
{
  "title": "How to integrate Fireflies MCP with LlamaIndex",
  "toolkit": "Fireflies",
  "toolkit_slug": "fireflies",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/fireflies/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/fireflies/framework/llama-index.md",
  "updated_at": "2026-05-12T10:11:43.106Z"
}
```

## Introduction

This guide walks you through connecting Fireflies to LlamaIndex using the Composio tool router. By the end, you'll have a working Fireflies agent that can transcribe this uploaded meeting audio file, summarize your last five recorded calls, list all transcripts involving the marketing team through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Fireflies account through Composio's Fireflies MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Fireflies with

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

The Fireflies MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fireflies account. It provides structured and secure access to your voice conversations, so your agent can perform actions like transcribing meetings, summarizing discussions, searching transcripts, and managing audio files on your behalf.
- Automated meeting transcription: Instantly upload audio files or add the Fireflies bot to live meetings so your agent can generate accurate transcripts for later review.
- AI-powered conversation summarization: Let your agent fetch concise, actionable summaries of calls and meetings to help you quickly catch up or share insights with your team.
- Transcript search and retrieval: Ask your agent to find specific transcripts or extract key segments from past conversations using keywords, dates, or participant names.
- Audio file management: Effortlessly upload, organize, or delete audio files and transcripts right from your agent, keeping your conversation library up to date.
- User and team insights: Enable your agent to fetch user details or team-wide meeting data, so you can stay on top of collaboration and engagement.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `FIREFLIES_ADD_TO_LIVE` | Add to Live Meeting | The AddToLive Action allows you to add the Fireflies.ai bot to an ongoing meeting. Note: This action requires a paid Fireflies plan to add bots to meetings. |
| `FIREFLIES_CONTINUE_ASK_FRED_THREAD` | Continue AskFred Thread | Tool to continue an existing AskFred conversation thread with follow-up questions. This action CANNOT create new threads - it only works with existing thread IDs. Use when you need to maintain context from previous exchanges and ask additional questions about meeting data in the same conversation. To start a new thread, use FIREFLIES_CREATE_ASK_FRED_THREAD instead. |
| `FIREFLIES_CREATE_ASK_FRED_THREAD` | Create AskFred Thread | Tool to start a new AskFred conversation thread with a question about meetings. Use when you need to query meeting transcripts using natural language, either for a specific meeting or across multiple meetings with filters. Supports time-based queries and participant-focused queries. |
| `FIREFLIES_CREATE_BITE` | Create Bite | Tool to create a bite (short video or audio clip) from a transcript segment. Use when you need to extract a specific portion of a meeting recording with defined start and end times. |
| `FIREFLIES_DELETE_TRANSCRIPT_BY_ID` | Delete Transcript by ID | Permanently delete a transcript from the Fireflies account by its unique ID. This is a destructive action that cannot be undone. The transcript, along with its associated audio/video files and summaries, will be permanently removed. Rate limited to 10 requests per minute across all user tiers. Verify the target transcript via FIREFLIES_GET_TRANSCRIPTS and obtain explicit user confirmation before calling this tool. |
| `FIREFLIES_FETCH_AI_APP_OUTPUTS` | Fetch AI App Outputs | Tool to fetch AI App outputs for specific apps or transcripts. Use when you need to retrieve AI-generated results from Fireflies AI Apps for meetings. |
| `FIREFLIES_GET_ASK_FRED_THREAD` | Get AskFred Thread | Tool to get a specific AskFred conversation thread with full history. Use when retrieving a particular AskFred thread along with all its messages and conversation details. |
| `FIREFLIES_GET_ASK_FRED_THREADS` | Get AskFred Threads | Tool to retrieve a summary of all AskFred conversation threads for the current user. Use when you need to browse or list available AskFred conversations without fetching full message history. |
| `FIREFLIES_GET_BITE_BY_ID` | Get Bite by ID | Fetches details for a specific bite by ID. Requires a Fireflies plan that supports Bites and appropriate API scope. If the bite is not found, use FIREFLIES_GET_TRANSCRIPT_BY_ID to retrieve full transcript context instead. |
| `FIREFLIES_GET_BITES` | Get Transcripts | Fetches a list of bites (highlights) against input arguments. Bites are generated asynchronously after transcript completion — only call this after FIREFLIES_GET_TRANSCRIPT_BY_ID reports `status=completed`. Empty results are possible for valid meetings; use FIREFLIES_GET_TRANSCRIPT_BY_ID for full transcript context when bites are unavailable. |
| `FIREFLIES_GET_TRANSCRIPT_BY_ID` | Get Transcript by ID | Fetches details for a specific Fireflies transcript ID. Requires a paid Fireflies plan. Response is nested at data.outputs.data.transcript; fields like sentences and attendees can be null — handle gracefully. transcript.summary.action_items may be a single newline-delimited string rather than an array — split by line breaks instead of iterating as an array. Limit concurrent calls to ~3 and apply exponential backoff on 429 responses, respecting Retry-After headers. |
| `FIREFLIES_GET_TRANSCRIPTS` | Get Transcripts | Fetches a list of transcripts against input filters. Metadata filters (title, host_email, organizers, participants) match transcript metadata only, not spoken content. Pagination via skip/limit may trigger HTTP 429 on rapid requests; use backoff between pages. |
| `FIREFLIES_GET_USER_BY_ID` | Get User by ID | The GetUser Action is designed to fetch details associated with a specific user id. |
| `FIREFLIES_GET_USER_GROUPS` | Get User Groups | Tool to fetch a list of all user groups within the team with information about user groups including their members. Use when you need to retrieve team user groups, optionally filtering to only groups the current user belongs to with the mine parameter. |
| `FIREFLIES_GET_USERS` | Get Users | Fetches a list of all users within the team, including their full email addresses. Use to resolve complete email addresses from user names before passing to tools that require exact email addresses (no partial addresses or domain-only values). |
| `FIREFLIES_GRAPHQL_QUERY` | Execute GraphQL Query | Execute an authenticated, read-only Fireflies GraphQL operation (query) and return the full raw GraphQL response (data+errors) for reliable fallback and debugging. Use when higher-level tools fail due to schema mismatches or to access raw error details. |
| `FIREFLIES_SET_USER_ROLE` | Set User Role | Tool to update a user's role within a team. Use when you need to grant or revoke admin privileges. Only team administrators can execute this action. Teams must maintain at least one admin member at all times. |
| `FIREFLIES_UPDATE_MEETING_CHANNEL` | Update Meeting Channel | Tool to batch update channel assignments for 1-5 meeting transcripts. Use when you need to assign meetings to a specific channel. Requires meeting owner or team admin privileges. All-or-nothing semantics: if any transcript fails validation, none are updated. |
| `FIREFLIES_UPDATE_MEETING_PRIVACY` | Update Meeting Privacy | Tool to update the privacy setting of a meeting transcript. Use when you need to change meeting access permissions. Only meeting owners and team admins can update privacy settings. |
| `FIREFLIES_UPDATE_MEETING_TITLE` | Update Meeting Title | Tool to update the title of a meeting transcript. Use when you need to rename a meeting. Requires admin privileges and the meeting owner must be in your team. |
| `FIREFLIES_UPLOAD_AUDIO` | Upload Audio | The UploadAudio Action allows you to upload audio files to Fireflies.ai for transcription. Transcription is asynchronous — after submission, results may take several minutes to become available; use transcript retrieval tools to poll for completion. Note: This action requires a paid Fireflies plan to upload and transcribe audio files. |

## Supported Triggers

| Trigger slug | Name | Description |
|---|---|---|
| `FIREFLIES_TRANSCRIPTION_COMPLETE` | Transcription Complete Trigger | Triggers when a transcription is complete. Polls Fireflies API for transcripts created or updated since the last poll time. Handles rate limiting gracefully. |

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

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

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

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 Fireflies 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, fireflies)
- 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 Fireflies 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=["fireflies"],
    )

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

  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 Fireflies 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 Fireflies
```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 Fireflies, 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=["fireflies"],
    )

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

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

- [ChatGPT](https://composio.dev/toolkits/fireflies/framework/chatgpt)
- [Antigravity](https://composio.dev/toolkits/fireflies/framework/antigravity)
- [OpenAI Agents SDK](https://composio.dev/toolkits/fireflies/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/fireflies/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/fireflies/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/fireflies/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/fireflies/framework/codex)
- [Cursor](https://composio.dev/toolkits/fireflies/framework/cursor)
- [VS Code](https://composio.dev/toolkits/fireflies/framework/vscode)
- [OpenCode](https://composio.dev/toolkits/fireflies/framework/opencode)
- [OpenClaw](https://composio.dev/toolkits/fireflies/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/fireflies/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/fireflies/framework/cli)
- [Google ADK](https://composio.dev/toolkits/fireflies/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/fireflies/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/fireflies/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/fireflies/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/fireflies/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.
- [Dovetail](https://composio.dev/toolkits/dovetail) - Dovetail is a research analysis platform for transcript review and insight generation. It helps teams code interviews, analyze feedback, and create actionable research summaries.
- [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.

## Frequently Asked Questions

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

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

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

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

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