How to integrate Fingertip MCP with Vercel AI SDK v6

This guide walks you through connecting Fingertip to Vercel AI SDK v6 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 Vercel AI SDK 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.

Get started for free Get a demo

Fingertip

Api Key

Fingertip is a business management platform for selling, booking, and customer engagement—all from a single link. It helps businesses streamline operations and connect with customers across social channels.

60 Tools

Managed auth

Connect Fingertip without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

This guide will help you understand how to give your Vercel AI SDK 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

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Fingertip integration
Using Composio's Tool Router to dynamically load and access Fingertip tools
Creating an MCP client connection using HTTP transport
Building an interactive CLI chat interface with conversation history management
Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

streamText: Core function for streaming responses with real-time tool support
MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
OpenAI Provider: Native integration with OpenAI models

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.

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:

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

Step-by-step Guide

Step by step09 STEPS

Prerequisites

Before you begin, make sure you have:

Node.js and npm installed
A Composio account with API key
An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key

Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
Keep the API key safe.

Composio API Key

Log in to the Composio dashboard.
Navigate to your API settings and generate a new API key.
Store this key securely as you'll need it for authentication.

Install required dependencies

bash

npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

@ai-sdk/openai: Vercel AI SDK's OpenAI provider
@ai-sdk/mcp: MCP client for Vercel AI SDK
@composio/core: Composio SDK for tool integration
ai: Core Vercel AI SDK
dotenv: Environment variable management

Set up environment variables

bash

OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

OPENAI_API_KEY: Your OpenAI API key for GPT model access
COMPOSIO_API_KEY: Your Composio API key for tool access
COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

What's happening:

We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
The dotenv/config import automatically loads environment variables
The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["fingertip"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Fingertip tools
The create method takes the user ID and specifies which toolkits should be available
The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
This session provides access to all Fingertip-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript

const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();

What's happening:

We're creating an MCP client that connects to our Composio Tool Router session via HTTP
The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
The type: "http" is important - Composio requires HTTP transport
tools() retrieves all available Fingertip tools that the agent can use

Initialize conversation and CLI interface

typescript

let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to fingertip, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

What's happening:

We initialize an empty messages array to maintain conversation history
A readline interface is created to accept user input from the command line
Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

What's happening:

We use streamText instead of generateText to stream responses in real-time
toolChoice: "auto" allows the model to decide when to use Fingertip tools
stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
onStepFinish callback displays which tools are being used in real-time
We iterate through the text stream to create a typewriter effect as the agent responds
The complete response is added to conversation history to maintain context
Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Fingertip and Vercel AI SDK:

typescript

import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["fingertip"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to fingertip, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Fingertip agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

Real-time streaming responses for a better user experience with typewriter effect
Live tool execution feedback showing which tools are being used as the agent works
Dynamic tool loading through Composio's Tool Router with secure authentication
Multi-step tool execution with configurable step limits (up to 10 steps)
Comprehensive error handling for robust agent execution
Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

TOOLS

Supported Tools

Every Fingertip action and event your agent gets out of the box.

Create Store Invoice

Tool to create a store invoice in Fingertip.

Create Invoice Item

Creates a new invoice item for a Fingertip site.

Create Page

Tool to create a new page within a Fingertip site.

Create Page Block

Creates a new block within the specified page.

Create Fingertip Site

Creates a new Fingertip site with the specified configuration.

Create Site Contact

Tool to create a new contact associated with a site including marketing preferences.

Create Site Invitation

Tool to create a new invitation for a user to join a site.

Create Webhook Subscription

Tool to create a webhook subscription for receiving real-time event notifications from Fingertip.

Delete Block

Tool to permanently delete a block by its ID.

Delete Draft Invoice

Tool to delete a draft store invoice.

Delete Invoice Item

Tool to delete a Fingertip invoice item.

Delete Fingertip Page

Tool to permanently delete a page and all associated data.

Delete Fingertip Site

Tool to delete a Fingertip site.

Delete Site Invitation

Tool to delete a site invitation by its ID.

Delete Site Membership

Tool to delete a specific site membership.

Delete Webhook

Tool to remove an existing webhook subscription.

Delete Workspace Invitation

Tool to delete a workspace invitation by its ID.

Get Block

Tool to retrieve a specific block by its ID.

Get Comprehensive Site Analytics

Tool to retrieve comprehensive analytics for a specific site.

Get Invoice Item

Tool to retrieve details of a specific invoice item by its ID.

Get Page

Tool to retrieve a specific Fingertip page by its ID.

Get Page Theme

Retrieve the theme configuration for a specific page.

Get Fingertip Site

Tool to retrieve a specific Fingertip site by its UUID.

Get Webhook

Tool to retrieve a specific webhook by ID with its related triggers.

Health Check

Tool to verify API connectivity.

List Fingertip Blog Posts

Tool to list published blog posts for a specific site.

List Bookings

Tool to retrieve a paginated list of bookings for a site with optional status filtering.

List Event Types

Tool to list event types for a specific site.

List Form Responses

Tool to retrieve form responses for a specific form template and site.

List Form Templates

Tool to retrieve a paginated list of form templates.

List Invoice Items

Tool to list invoice items for a specific Fingertip site.

List Fingertip Invoices

Tool to retrieve a paginated list of invoices for sites the user has access to.

List Fingertip Messages

Tool to retrieve a paginated list of messages for a site.

List Orders

Tool to retrieve orders with basic information for a specific site.

List Page Blocks

Tool to retrieve all blocks associated with a specific page.

List Pages

List all pages for a specific Fingertip site.

List Page Themes

Tool to retrieve a paginated list of page themes.

List Quotes

List all quotes for a specific Fingertip site.

List Sample Bookings

Tool to retrieve sample bookings for testing and development purposes.

List Sample Form Responses

Tool to retrieve sample form responses for a specific form template.

List Sample Orders

Tool to retrieve sample orders for testing purposes.

List Sample Site Contacts

Tool to retrieve sample site contacts with basic information.

List Site Contacts

Tool to retrieve site contacts with basic contact information and engagement metrics.

List Site Invitations

Tool to retrieve a paginated list of invitations for a specific site.

List Site Memberships

Tool to retrieve a paginated list of site memberships.

List Sites

Tool to retrieve a paginated list of sites accessible by the API key.

List Webhooks

Tool to retrieve a paginated list of webhooks with optional filtering and sorting.

List Workspaces

Tool to retrieve a paginated list of workspaces accessible to the API key.

Mark Invoice as Paid

Tool to mark a store invoice as paid in Fingertip.

Patch Page Theme

Apply JSON Patch operations to page theme content following RFC 6902.

Search Help Articles

Tool to search help documentation articles by query string.

Send Store Invoice

Tool to send a store invoice to a customer.

Send Fingertip Quote

Tool to send a store quote by its UUID.

Update Block

Updates an existing block with the provided data.

Update Invoice Item

Tool to update an invoice item in Fingertip.

Update Page

Tool to update an existing Fingertip page with new data.

Update Page Theme

Tool to update the theme configuration for a specific page.

Update Fingertip Quote

Tool to update an existing Fingertip store quote.

Update Fingertip Site

Updates an existing Fingertip site with provided partial data.

Update Webhook

Tool to update an existing Fingertip webhook subscription.

FRAMEWORKS

How to build Fingertip MCP Agent with another framework

OpenAI Agents SDK

Use Fingertip MCP with OpenAI Agents SDK

Claude Agent SDK

Use Fingertip MCP with Claude Agent SDK

Claude Code

Use Fingertip MCP with Claude Code

Claude Cowork

Use Fingertip MCP with Claude Cowork

Codex

Use Fingertip MCP with Codex

OpenClaw

Use Fingertip MCP with OpenClaw

Hermes

Use Fingertip MCP with Hermes

CLI

Use Fingertip MCP with CLI

Google ADK

Use Fingertip MCP with Google ADK

LangChain

Use Fingertip MCP with LangChain

Mastra AI

Use Fingertip MCP with Mastra AI

LlamaIndex

Use Fingertip MCP with LlamaIndex

CrewAI

Use Fingertip MCP with CrewAI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Addresszen

Api Key

Addresszen is a real-time address autocomplete and verification service. It helps capture accurate, deliverable addresses with instant suggestions and validation.

Asin data api

Api Key

Asin data api gives you detailed, real-time product data from Amazon, including price, rank, and reviews. Perfect for e-commerce pros and data-driven marketers who need instant marketplace insights.

Baselinker

Api Key

BaseLinker is an all-in-one e-commerce management platform connecting stores, marketplaces, carriers, and more. It streamlines order processing, inventory control, and automates your sales operations.

Bestbuy

Api Key

Best Buy is a leading retailer offering APIs for product, store, and recommendation data. Instantly access up-to-date retail insights for smarter shopping and decision-making.

FAQ

Frequently asked questions

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.

Yes, you can. Vercel AI SDK v6 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.

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.

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.

Start with Fingertip.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Fingertip tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies

How to integrate Fingertip MCP with Vercel AI SDK v6

Connect Fingertip without auth hassles

Introduction

Also integrate Fingertip with

TL;DR

What is Vercel AI SDK?

What is the Fingertip MCP server, and what's possible with it?

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

Handle user input and stream responses with real-time tool feedback

Complete Code

Conclusion

Supported Tools

How to build Fingertip MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Addresszen

Asin data api

Baselinker

Bestbuy

Frequently asked questions

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

Can I use Tool Router MCP with Vercel AI SDK v6?+

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

How safe is my data with Composio Tool Router?+

Start with Fingertip.It takes 30 seconds.

Teams ship real agents on Composio