How to integrate Ramp MCP with Vercel AI SDK v6

This guide walks you through connecting Ramp to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ramp agent that can download last month's statement as pdf, list all transactions over $500 this week, get details of your virtual cards through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Ramp account through Composio's Ramp MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Ramp logoRamp
Oauth2

Ramp is a finance automation platform for tracking business expenses and income. It helps you manage spending and gain actionable insights into your company's finances.

88 Tools

Introduction

This guide walks you through connecting Ramp to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ramp agent that can download last month's statement as pdf, list all transactions over $500 this week, get details of your virtual cards through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Ramp account through Composio's Ramp MCP server.

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

Also integrate Ramp with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Ramp integration
  • Using Composio's Tool Router to dynamically load and access Ramp 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 Ramp MCP server, and what's possible with it?

The Ramp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ramp account. It provides structured and secure access to your company's financial data, so your agent can fetch transactions, analyze card activity, generate statements, manage departments, and retrieve detailed expense information on your behalf.

  • Comprehensive transaction tracking: Instantly pull lists of all your business transactions or your own card activity, making it easy to monitor expenses and spot anomalies.
  • Card management and insights: Retrieve details about specific Ramp cards or see all cards assigned to you, including limits, status, and cardholder info for better financial oversight.
  • Automated statement generation: Ask your agent to generate and download account statements in multiple formats (PDF, CSV, JSON) for reporting or bookkeeping.
  • Department and organizational management: Create new departments or fetch detailed department profiles to help structure your expense tracking and categorize spending.
  • Detailed transaction analysis: Dive into specific transactions to get merchant information, receipts, dispute details, and accounting codes for audit and compliance purposes.

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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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
6

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: ["ramp"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Ramp 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 Ramp-related tools through the MCP protocol
7

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 Ramp tools that the agent can use
8

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 ramp, 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
9

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 Ramp 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 Ramp 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: ["ramp"],
  });

  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 ramp, 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 Ramp 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 Ramp action and event your agent gets out of the box.

Create Department

Tool for creating a new department in your Ramp organization.

Create Inventory Item Accounting Field

Tool to create a new inventory item accounting field for tracking inventory categories.

Create Transaction Memo

Tool for uploading a new memo for a transaction in Ramp.

Create Mileage Reimbursement

Tool to create a mileage reimbursement in Ramp.

Create New Custom Accounting Field

Tool for creating a new custom accounting field.

Create Tax Code Accounting Field

Tool to create a new tax code accounting field in Ramp.

Create User Invite

Tool to create a user invite for onboarding new employees to Ramp.

Create Webhook Subscription

Tool to create a new webhook subscription for receiving event notifications from Ramp.

Deactivate User

Tool to deactivate a user in your Ramp organization.

Delete Accounting GL Account

Tool to delete a general ledger account from Ramp.

Delete Accounting Connection

Tool to disconnect the current active API-based accounting connection.

Delete Custom Accounting Field

Tool to delete a custom accounting field from Ramp.

Delete Accounting Inventory Item Option

Tool to delete an accounting inventory item option from Ramp.

Delete Tax Code Accounting Field

Tool to delete the tax code accounting field from Ramp.

Delete Accounting Tax Code Option

Tool to delete a tax code option from Ramp.

Delete Accounting Tax Rate

Tool to delete an accounting tax rate from Ramp.

Delete Accounting Vendor

Tool to delete an accounting vendor from Ramp.

Delete Custom Field Option

Tool to delete a custom accounting field option from Ramp.

Delete Inventory Item Field

Tool to delete the inventory item accounting field from Ramp.

Remove Users from Shared Limit

Tool to remove users from a shared spend limit in Ramp.

Delete Webhook Subscription

Tool to delete a webhook subscription by ID.

Fetch General Ledger Account

Tool to fetch a specific general ledger account by ID from Ramp.

Fetch Accounting Vendor

Tool to fetch a specific accounting vendor by ID from Ramp.

Fetch Custom Accounting Field

Tool for fetching a custom accounting field.

List General Ledger Accounts

Tool to list general ledger accounts from Ramp.

Fetch All Accounting Connections

Tool to fetch all accounting connections for the current Ramp business.

Get Accounting Connection

Tool to fetch the current active accounting connection for a Ramp account.

Fetch Accounting Connection By ID

Tool to fetch a specific accounting connection by ID from Ramp.

List Custom Accounting Fields

Tool to list custom accounting fields for coding transactions.

List Accounting Vendors

Tool to list accounting vendors from Ramp.

Get All Transactions

Get all the transactions.

Get Card

Tool for retrieving detailed information about a specific card.

Get Card Vault Resource

Tool to fetch a card's sensitive details from the vault.

Get Custom Field Option

Tool to fetch a custom accounting field option by its ID.

Get Department

Tool for retrieving detailed information about a specific department.

Get Inventory Item Field

Tool to fetch inventory item accounting field for the current accounting connection.

Get Memo

Tool to fetch a transaction memo.

Get Reimbursement Details

Tool for retrieving complete details of a specific reimbursement.

Get Spend Limit

Tool to fetch detailed information about a specific spend limit.

Get Statement

Tool for retrieving statement details or downloading statements.

Get Transaction Details

Tool for retrieving complete details of a specific transaction.

Get User

Tool to retrieve detailed information about a specific Ramp user by their ID.

Get Users Deferred Status

Tool for fetching the status of a deferred user task.

Get Vendor Details

Tool for retrieving detailed information about a specific vendor.

Get Webhook

Tool to retrieve detailed information about a specific webhook subscription by ID.

Issue Virtual Card

Tool for issuing virtual cards to users instantly.

List Accounting Inventory Item Options

Tool to list accounting inventory item options from Ramp.

List Accounting Tax Rates

Tool to list tax rates from Ramp's accounting integration.

List All Cards

Tool for listing all cards across the organization with optional filters.

List Departments

Tool for listing all departments in the organization.

List Memos

Tool for listing memos associated with transactions in your Ramp organization.

List Reimbursements

Tool for listing reimbursements with comprehensive filtering options.

List Statements

Tool for listing all statements with filtering options.

List Users

Tool for listing users in your Ramp organization with flexible filtering.

List Vendors

Tool for listing vendors with their spending information.

List Vendor Bank Accounts

Tool for listing bank accounts associated with a specific vendor.

List Vendor Contacts

Tool for listing contacts associated with a specific vendor.

List Vendor Credits

Tool to list all vendor credits for all vendors of a business.

List Webhooks

Tool for listing all webhook subscriptions for the organization.

Options for Custom Accounting Field

Tool for listing options for a given accounting field.

Update Accounting Connection

Tool to update an accounting connection's settings.

Update Card

Tool to update a card's properties including owner, display name, and spending restrictions.

Update Custom Field Option

Tool to update a custom accounting field option.

Update General Ledger Account

Tool to update a general ledger account in Ramp.

Update Inventory Item Field

Tool to update the inventory item accounting field for a Ramp connection.

Upload Accounting GL Accounts

Tool to batch upload general ledger accounts to Ramp.

Create Accounting Connection

Tool to register a new API-based accounting connection between Ramp and an accounting provider.

Upload Accounting Vendors

Tool to batch upload vendors to Ramp for coding transactions, bills, and purchase orders.

Upload Inventory Item Options

Tool to upload inventory item options for an active inventory item accounting field.

Create Physical Card

Tool to create a physical card asynchronously.

Reactivate Accounting Connection

Tool to reactivate a previously unlinked accounting connection by changing its status back to linked.

Reactivate User

Tool to reactivate a suspended user in your Ramp organization.

Submit Reimbursement Receipt

Tool to upload a receipt for a reimbursement.

Suspend Card

Tool to suspend a card by creating an async task that locks the card from use.

Terminate Card

Tool to permanently terminate a Ramp card.

Update Custom Accounting Field

Tool to update a custom accounting field.

Update Accounting Inventory Item Option

Tool to update an inventory item option in Ramp's accounting system.

Update Accounting Tax Code

Tool to update tax code accounting field.

Update Accounting Tax Code Option

Tool to update a tax code option in Ramp.

Update Accounting Tax Rate

Tool to update an accounting tax rate in Ramp.

Update Accounting Vendor

Tool to update an accounting vendor in Ramp.

Update Card Spending Limit

Tool for updating spending limits on a card.

Update Department

Tool for updating an existing department in your Ramp organization.

Update Spending Limit

Tool to update a spending limit in Ramp.

Update User

Tool to update an existing user in your Ramp organization.

Upload New Options for Custom Accounting Field

Tool for uploading new options for a given accounting field.

Upload Tax Code Options

Tool to upload tax code options to Ramp.

Upload Accounting Tax Rates

Tool to batch upload tax rates to Ramp.

FRAMEWORKS

How to build Ramp MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ramp MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ramp MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Ramp MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ramp MCP with Claude Cowork

Codex logo

Codex

Use Ramp MCP with Codex

OpenClaw logo

OpenClaw

Use Ramp MCP with OpenClaw

Hermes logo

Hermes

Use Ramp MCP with Hermes

CLI logo

CLI

Use Ramp MCP with CLI

Google ADK logo

Google ADK

Use Ramp MCP with Google ADK

LangChain logo

LangChain

Use Ramp MCP with LangChain

Mastra AI logo

Mastra AI

Use Ramp MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ramp MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ramp MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Ramp.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

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
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
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
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
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
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
Jerome Leclanche
Co-Founder, Ingram Technologies