# How to integrate Fibery MCP with LlamaIndex

```json
{
  "title": "How to integrate Fibery MCP with LlamaIndex",
  "toolkit": "Fibery",
  "toolkit_slug": "fibery",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/fibery/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/fibery/framework/llama-index.md",
  "updated_at": "2026-05-12T10:11:15.959Z"
}
```

## Introduction

This guide walks you through connecting Fibery to LlamaIndex using the Composio tool router. By the end, you'll have a working Fibery agent that can list all open tasks for your team, fetch details for project entity by id, delete file attachment from a task through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Fibery account through Composio's Fibery MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Fibery with

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

The Fibery MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fibery account. It provides structured and secure access to your workspace data, so your agent can perform actions like querying entities, managing custom apps, running GraphQL queries, and organizing files—all with zero manual integration code.
- Entity query and retrieval: Instantly fetch detailed information or lists of entities based on type, filters, and fields, making it easy to surface project or task data as needed.
- Custom app and endpoint management: Let your agent list, inspect, or delete custom apps and endpoints, streamlining workspace configuration and app lifecycle management.
- Flexible data manipulation with GraphQL: Execute custom GraphQL queries and mutations against your Fibery space to fetch, update, or manipulate structured data programmatically.
- File and resource cleanup: Remove outdated files or entities efficiently, helping keep your workspace organized and clutter-free with automated deletions.
- Authentication and workspace insights: Validate tokens securely and retrieve workspace or app metadata, ensuring your agent always operates with up-to-date context and permissions.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `FIBERY_DELETE_CUSTOM_APP_ENDPOINT` | Delete Custom App Endpoint | Tool to delete a specific custom app endpoint. Use after confirming the app and endpoint IDs to remove. |
| `FIBERY_DELETE_ENTITY` | Delete Entity | Permanently delete a Fibery entity by its UUID and type. Use this action when you need to remove an entity from the workspace. Requires both the entity's UUID and its full qualified type name. WARNING: Deletion is irreversible. Example: Delete a task with entity_id='550e8400-e29b-41d4-a716-446655440000' and type='Tasks/Task'. |
| `FIBERY_DELETE_FILE` | Delete File | Delete a file from Fibery storage using its secret identifier. Use this action to permanently remove an uploaded file. You must provide the file's secret (fibery/secret), not its ID (fibery/id). The secret is returned when you upload a file or can be queried via the commands API. |
| `FIBERY_EXECUTE_GRAPH_QL_QUERY` | Execute GraphQL Query | Execute GraphQL queries or mutations against a Fibery workspace. Fibery organizes data into Spaces, each with its own GraphQL schema containing entity types and operations. This action automatically tries common space names if no space is specified, making it easy to use without prior knowledge. Best practices: - Start with introspection queries to discover schema: { __schema { types { name } } } - Use { __type(name: "Query") { fields { name } } } to see available queries - Space names typically match your workspace app/database names - The action returns both data and errors (GraphQL can return partial results) |
| `FIBERY_GET_APP_INFO` | Get App Information | Tool to retrieve application information. Use when you need the version, name, description, authentication methods, and available data sources before further operations. |
| `FIBERY_GET_CUSTOM_APP_ENDPOINTS` | Get Custom App Endpoints | Tool to list custom app endpoints. Use when you need the available custom endpoints for a given app before invoking them. |
| `FIBERY_GET_CUSTOM_APPS` | Get Custom Apps | Tool to list all custom apps in the Fibery workspace. Use when you need the identifiers of all custom apps. |
| `FIBERY_GET_FILE` | Get File | Download a file from Fibery by its secret or ID. Use this tool to retrieve file content from Fibery storage. The file secret is a UUID that uniquely identifies a file and is the preferred identifier. You can obtain the file secret: - From the 'fibery/secret' field when querying entities that have file fields - From the 'url' field in upload file response (extract the UUID from the URL) - From rich text content where files are embedded as /api/files/{secret} |
| `FIBERY_GET_GRAPH_QL_SCHEMA` | Get GraphQL Schema | Retrieves the GraphQL schema for the Fibery workspace using standard GraphQL introspection. Returns the schema as a JSON string that includes all types, queries, mutations, and their fields. Use this to discover available GraphQL operations before executing queries. |
| `FIBERY_GET_USER_PREFERENCES` | Get User Preferences | Tool to retrieve the current user's UI preferences. Use after authentication to tailor UI to user settings. |
| `FIBERY_POST_AUTH_REFRESH_TOKEN` | Refresh access token | Tool to validate and refresh an access token. For Fibery's standard API, this validates the current token is still working (Fibery tokens don't expire). For OAuth2 integrations with third-party services, this could be used to refresh tokens through the validate endpoint. |
| `FIBERY_POST_AUTH_TOKEN` | Validate Fibery authentication and get access token | Validates Fibery API authentication and returns the active access token. This action validates that your API token is working correctly by attempting to query the Fibery API. For standard Fibery workspaces, it validates the pre-configured API token from the Authorization header. Behavior: 1. First attempts OAuth2 password grant at /auth/token (rare, only custom installations) 2. If /auth/token returns 404 (standard case), validates existing token via /commands endpoint 3. Returns the validated token that can be used for subsequent API calls The returned access_token should be used in the header: `Authorization: Token ` Note: Most Fibery workspaces use pre-generated API tokens (created in workspace settings), not username/password authentication. The username/password parameters are only used if a custom OAuth2 endpoint exists. |
| `FIBERY_POST_CREATE_ENTITY` | Create Entity | Tool to create a new Fibery entity. Use when you have prepared all necessary field values and need to persist a new record. Example: Create a 'Project/Task' with title and assignee. |
| `FIBERY_POST_FETCH_DATA_COUNT` | Count Entities by Type | Count the total number of entities for a given Fibery type (database). This tool queries the Fibery workspace to return how many entities exist for the specified type. Use it to get totals like "how many users", "how many features", etc. Authentication: Requires a valid Fibery API token with read access. |
| `FIBERY_POST_FETCH_DATA_LIST` | Fetch Datalist Options | Fetches one page of distinct values for a specific field from a Fibery entity type. Returns a list of unique options that can be used for filtering, dropdowns, or autocomplete. ONE Fibery API call is made per invocation; pagination is caller-driven via the `offset` and `limit` request fields and the `next_offset` response field. The action first attempts the `/datalist` endpoint and, if that endpoint is unavailable on the workspace (404/405/501), falls back to a single `fibery.entity/query` command via `/commands`. |
| `FIBERY_POST_FETCH_SCHEMA` | Fetch Schema | Fetch the complete schema metadata for a Fibery workspace. Returns all types (entities) and their fields, including system types (fibery/user, fibery/app) and user-defined types (MySpace/Task, etc.). Use this to discover available types before querying data or to understand the structure of your workspace. |
| `FIBERY_POST_OAUTH2_ACCESS_TOKEN` | Exchange OAuth2 authorization code | Exchange an OAuth2 authorization code for access and refresh tokens. This action is used during the final step of the OAuth2 authorization code flow when building Fibery custom integration apps. After a user authorizes your app on a third-party service and is redirected back with an authorization code, use this endpoint to exchange that code for access tokens. Important: This endpoint is typically implemented by YOUR custom integration app (connector), not by Fibery itself. The action probes multiple common endpoint paths across your app's base URL and Fibery's OAuth service to maximize compatibility. Typical flow: 1. User initiates OAuth authorization via /oauth2/v1/authorize 2. User approves on the third-party service 3. Third-party redirects to callback_uri with an authorization code 4. Call THIS endpoint with the code to get access/refresh tokens |
| `FIBERY_POST_REVOKE_TOKEN` | Delete/Revoke Access Token | Delete/revoke an existing Fibery API access token by its ID. Uses the DELETE /api/tokens/:token_id endpoint to permanently remove an API token. Important: This endpoint typically requires cookie-based authentication (browser session). When using API token authentication, you may receive a 401 Unauthorized error. Use this when you need to invalidate a specific API token, such as during security rotation or when revoking access for a specific integration. |
| `FIBERY_POST_VALIDATE_ACCOUNT` | Validate Fibery Workspace Credentials | Validates Fibery workspace credentials by performing a test API query to retrieve the authenticated user's name. This action verifies that the provided credentials (or existing metadata credentials) are valid and have access to the workspace. Use this to confirm authentication before executing other Fibery operations. Supports multiple authentication types: workspace tokens, API keys, basic auth, and OAuth2. |
| `FIBERY_POST_VALIDATE_FILTER` | Validate Filter | Validates filter definitions before executing data queries. Use this tool to verify that a filter's structure and syntax are correct without actually fetching data. For Fibery workspaces: Validates by executing a safe test query with limit=1. For custom apps: Calls the app's POST /validate/filter endpoint if available. Returns validation result indicating whether the filter can be safely used. |
| `FIBERY_UPDATE_ENTITY` | Update Entity | Update an existing Fibery entity's fields. Use this to modify text fields, numbers, single-select states, workflow states, or relation fields on an entity. Prerequisites: - You need the entity's UUID (fibery/id) - obtain via Get Entities or Create Entity. - You need the fully-qualified type name (e.g., 'Engineering/Task'). - For workflow/state fields, you need the state's UUID. Limitations: - Rich text fields cannot be updated via this command. - Entity collection fields should be updated after entity creation. |
| `FIBERY_UPDATE_USER_PREFERENCES` | Update User Preferences | Tool to update the current user's preferences by using the Commands API. It fetches the current user id and preferences, merges the provided payload, and writes back the merged object into 'fibery/ui-preferences' of the current fibery/user. |
| `FIBERY_UPLOAD_FILE` | Upload File | Upload a file to Fibery's file storage. Use this action to upload files that can later be attached to entities or used in documents. Returns file metadata including the file ID and secret needed for subsequent operations. |

## Supported Triggers

None listed.

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

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

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

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 Fibery 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, fibery)
- 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 Fibery 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=["fibery"],
    )

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

  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 Fibery 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 Fibery
```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 Fibery, 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=["fibery"],
    )

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

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

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

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.
- [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.

## Frequently Asked Questions

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

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

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

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

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