How to integrate Fingertip MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Fingertip logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Fingertip to LlamaIndex using the Composio tool router. By the end, you'll have a working Fingertip agent that can show analytics for your main fingertip site, list all upcoming event types for your business, get summaries of recent blog posts through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Fingertip account through Composio's Fingertip MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Fingertip with

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

The Fingertip MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fingertip account. It provides structured and secure access to your business management dashboard, so your agent can perform actions like creating and deleting sites, retrieving site analytics, managing memberships, and listing blog posts or event types on your behalf.

  • Instant site creation and removal: Let your agent create new Fingertip sites or delete existing ones as your business evolves.
  • Comprehensive site analytics retrieval: Ask your agent to fetch detailed analytics and performance metrics for specific sites, including store activity over selected time periods.
  • Membership and invitation management: Have your agent add, remove, or look up site memberships and cancel outstanding workspace invitations easily.
  • Blog and content organization: Direct your agent to list published blog posts, retrieve post summaries, and sort or paginate results for content management.
  • Event and form template listing: Enable your agent to fetch available event types and form templates to streamline client bookings or data collection.

Supported Tools & Triggers

Tools
Create Store InvoiceTool to create a store invoice in Fingertip.
Create Invoice ItemCreates a new invoice item for a Fingertip site.
Create PageTool to create a new page within a Fingertip site.
Create Page BlockCreates a new block within the specified page.
Create Fingertip SiteCreates a new Fingertip site with the specified configuration.
Create Site ContactTool to create a new contact associated with a site including marketing preferences.
Create Site InvitationTool to create a new invitation for a user to join a site.
Create Webhook SubscriptionTool to create a webhook subscription for receiving real-time event notifications from Fingertip.
Delete BlockTool to permanently delete a block by its ID.
Delete Draft InvoiceTool to delete a draft store invoice.
Delete Invoice ItemTool to delete a Fingertip invoice item.
Delete Fingertip PageTool to permanently delete a page and all associated data.
Delete Fingertip SiteTool to delete a Fingertip site.
Delete Site InvitationTool to delete a site invitation by its ID.
Delete Site MembershipTool to delete a specific site membership.
Delete WebhookTool to remove an existing webhook subscription.
Delete Workspace InvitationTool to delete a workspace invitation by its ID.
Get BlockTool to retrieve a specific block by its ID.
Get Comprehensive Site AnalyticsTool to retrieve comprehensive analytics for a specific site.
Get Invoice ItemTool to retrieve details of a specific invoice item by its ID.
Get PageTool to retrieve a specific Fingertip page by its ID.
Get Page ThemeRetrieve the theme configuration for a specific page.
Get Fingertip SiteTool to retrieve a specific Fingertip site by its UUID.
Get WebhookTool to retrieve a specific webhook by ID with its related triggers.
Health CheckTool to verify API connectivity.
List Fingertip Blog PostsTool to list published blog posts for a specific site.
List BookingsTool to retrieve a paginated list of bookings for a site with optional status filtering.
List Event TypesTool to list event types for a specific site.
List Form ResponsesTool to retrieve form responses for a specific form template and site.
List Form TemplatesTool to retrieve a paginated list of form templates.
List Invoice ItemsTool to list invoice items for a specific Fingertip site.
List Fingertip InvoicesTool to retrieve a paginated list of invoices for sites the user has access to.
List Fingertip MessagesTool to retrieve a paginated list of messages for a site.
List OrdersTool to retrieve orders with basic information for a specific site.
List Page BlocksTool to retrieve all blocks associated with a specific page.
List PagesList all pages for a specific Fingertip site.
List Page ThemesTool to retrieve a paginated list of page themes.
List QuotesList all quotes for a specific Fingertip site.
List Sample BookingsTool to retrieve sample bookings for testing and development purposes.
List Sample Form ResponsesTool to retrieve sample form responses for a specific form template.
List Sample OrdersTool to retrieve sample orders for testing purposes.
List Sample Site ContactsTool to retrieve sample site contacts with basic information.
List Site ContactsTool to retrieve site contacts with basic contact information and engagement metrics.
List Site InvitationsTool to retrieve a paginated list of invitations for a specific site.
List Site MembershipsTool to retrieve a paginated list of site memberships.
List SitesTool to retrieve a paginated list of sites accessible by the API key.
List WebhooksTool to retrieve a paginated list of webhooks with optional filtering and sorting.
List WorkspacesTool to retrieve a paginated list of workspaces accessible to the API key.
Mark Invoice as PaidTool to mark a store invoice as paid in Fingertip.
Patch Page ThemeApply JSON Patch operations to page theme content following RFC 6902.
Search Help ArticlesTool to search help documentation articles by query string.
Send Store InvoiceTool to send a store invoice to a customer.
Send Fingertip QuoteTool to send a store quote by its UUID.
Update BlockUpdates an existing block with the provided data.
Update Invoice ItemTool to update an invoice item in Fingertip.
Update PageTool to update an existing Fingertip page with new data.
Update Page ThemeTool to update the theme configuration for a specific page.
Update Fingertip QuoteTool to update an existing Fingertip store quote.
Update Fingertip SiteUpdates an existing Fingertip site with provided partial data.
Update WebhookTool to update an existing Fingertip webhook subscription.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

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 Fingertip account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Fingertip

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

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 Fingertip access

Import modules

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()

Create a new file called fingertip_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

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")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

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=["fingertip"],
    )

    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 Fingertip actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Fingertip actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

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, fingertip)
  • 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 Fingertip tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

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}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Fingertip database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

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!")

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 Fingertip

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Fingertip, then start asking questions.

Complete Code

Here's the complete code to get you started with Fingertip and LlamaIndex:

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=["fingertip"],
    )

    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 Fingertip actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Fingertip 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!")

Conclusion

You've successfully connected Fingertip to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Fingertip 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 Fingertip MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Fingertip MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Fingertip MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Fingertip MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Fingertip MCP with Claude Cowork

Codex logo

Codex

Use Fingertip MCP with Codex

OpenClaw logo

OpenClaw

Use Fingertip MCP with OpenClaw

Hermes logo

Hermes

Use Fingertip MCP with Hermes

CLI logo

CLI

Use Fingertip MCP with CLI

Google ADK logo

Google ADK

Use Fingertip MCP with Google ADK

LangChain logo

LangChain

Use Fingertip MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Fingertip MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Fingertip MCP with Mastra AI

CrewAI logo

CrewAI

Use Fingertip MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Fingertip MCP?

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

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

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

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗