How to integrate Flutterwave MCP with Vercel AI SDK v6

This guide walks you through connecting Flutterwave to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Flutterwave agent that can create a payment link for a new order, generate virtual account numbers for customers, fetch details of a specific subaccount through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Flutterwave account through Composio's Flutterwave 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
Flutterwave logoFlutterwave
Api Key

Flutterwave is a global payments platform enabling businesses to accept and send payments across Africa and beyond. Its robust APIs simplify cross-border transactions and financial operations.

53 Tools

Introduction

This guide walks you through connecting Flutterwave to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Flutterwave agent that can create a payment link for a new order, generate virtual account numbers for customers, fetch details of a specific subaccount through natural language commands.

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

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

Also integrate Flutterwave 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 Flutterwave integration
  • Using Composio's Tool Router to dynamically load and access Flutterwave 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 Flutterwave MCP server, and what's possible with it?

The Flutterwave MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Flutterwave account. It provides structured and secure access to your payment infrastructure, so your agent can perform actions like creating payment links, managing beneficiaries, setting up virtual accounts, and handling subaccounts on your behalf.

  • Instant payment link creation: Let your agent generate hosted payment URLs for one-time or recurring transactions, making it easy to collect payments from customers.
  • Beneficiary management: Add, fetch, or remove transfer beneficiaries directly through your agent, streamlining the process of managing who receives your payouts.
  • Virtual account generation: Automatically create single or bulk virtual bank accounts for customers, enabling seamless and trackable bank transfers.
  • Subaccount setup and retrieval: Have your agent create, configure, or fetch subaccounts to manage split payments and disbursements for complex business needs.
  • Payment link control: Disable active payment links when necessary to prevent further transactions, ensuring you stay in control of your payment flows.

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: ["flutterwave"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Flutterwave 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 Flutterwave-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 Flutterwave 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 flutterwave, 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 Flutterwave 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 Flutterwave 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: ["flutterwave"],
  });

  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 flutterwave, 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 Flutterwave 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 Flutterwave action and event your agent gets out of the box.

Cancel Payment Plan

Tool to cancel a payment plan.

Create Beneficiary

Tool to create a new transfer beneficiary.

Create Bulk Tokenized Charge

Tool to create a bulk tokenized charge batch for charging multiple previously tokenized cards.

Create Bulk Virtual Account Numbers

Tool to create multiple virtual account numbers.

Create Payment Link

Tool to create a hosted payment link.

Create Payment Plan

Tool to create a new payment plan.

Create Refund

Tool to create a refund for a transaction.

Create Subaccount

Tool to create a new subaccount.

Create Virtual Account

Tool to create a new virtual account number.

Delete Beneficiary

Tool to delete a beneficiary by ID.

Delete Subaccount

Tool to delete a subaccount by ID.

Disable Payment Link

Tool to disable a Flutterwave payment link.

Fetch Beneficiary

Tool to retrieve details of a specific beneficiary by ID.

Fetch Subaccount

Tool to retrieve details of a specific subaccount by ID.

Generate Transaction Reference

Tool to generate a unique transaction reference.

Get All Subscriptions

Tool to retrieve all subscriptions, including cancelled ones.

Retrieve all transactions

Tool to retrieve a list of all transactions with optional filters.

Get All Wallet Balances

Tool to retrieve all wallet balances across currencies.

Get Balances per Currency

Tool to retrieve wallet balance for a specific currency.

Get Bank Branches

Tool to retrieve branch codes for a specific bank.

Get Banks by Country

Tool to retrieve all banks in a specified country.

Get Bill Categories

Tool to retrieve available bill categories.

Get Bulk Tokenized Charge Status

Tool to retrieve the status of a bulk tokenized charge operation by ID.

Get Bulk Virtual Account

Tool to fetch bulk virtual account details using batch ID.

Get Multiple Refund Transactions

Tool to retrieve multiple refund transactions with optional filters.

Get Payment Plan

Tool to retrieve details of a specific payment plan by ID.

Get Payment Plans

Tool to retrieve a list of all payment plans.

Get Refund

Tool to retrieve details of a specific refund by ID.

Get Transaction

Tool to retrieve details of a specific transaction by ID.

Get Transaction Fee

Tool to retrieve the fee for a specific transaction.

Get Transfer Fee

Tool to retrieve the fee for initiating a transfer.

Get Transfer Rates

Tool to retrieve exchange rates for transfers between currencies.

Get Virtual Account Number

Tool to fetch details of a virtual account number by order reference.

Get Wallet Statement

Tool to retrieve wallet balance history with optional filters.

Initiate BVN Verification

Tool to initiate BVN verification consent.

Initiate Mobile Money Tanzania

Tool to initiate a mobile money payment in Tanzania.

List All Beneficiaries

Tool to list all saved beneficiaries.

List Biller Products

Tool to retrieve all products available under a specific biller.

List Billers

Tool to retrieve available billers.

List Chargebacks

Tool to retrieve a list of chargebacks with optional filtering by Flutterwave reference.

List Payout Subaccount Refunds

Tool to list all payout subaccount refunds with pagination support.

List Payout Subaccounts

Tool to list all payout subaccounts.

List Recurring Bills

Tool to retrieve all recurring bill payments.

List all settlements

Tool to retrieve all settlements with optional filters.

List All Subaccounts

Tool to fetch all collection subaccounts.

List Transfers

Tool to fetch a list of bulk transfers from your Flutterwave account.

Resolve Bank Account

Tool to verify and resolve bank account details.

Resolve Card BIN

Tool to resolve and retrieve card BIN information from Flutterwave.

Update Payment Plan

Tool to update an existing payment plan.

Update Subaccount

Tool to update an existing subaccount.

Validate Bill Item

Tool to validate a bill service before payment.

Verify Transaction by Reference

Tool to verify a transaction using its transaction reference.

View Transaction Timeline

Tool to retrieve the event timeline for a transaction.

FRAMEWORKS

How to build Flutterwave MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Flutterwave MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Flutterwave MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Flutterwave MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Flutterwave MCP with Claude Cowork

Codex logo

Codex

Use Flutterwave MCP with Codex

OpenClaw logo

OpenClaw

Use Flutterwave MCP with OpenClaw

Hermes logo

Hermes

Use Flutterwave MCP with Hermes

CLI logo

CLI

Use Flutterwave MCP with CLI

Google ADK logo

Google ADK

Use Flutterwave MCP with Google ADK

LangChain logo

LangChain

Use Flutterwave MCP with LangChain

Mastra AI logo

Mastra AI

Use Flutterwave MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Flutterwave MCP with LlamaIndex

CrewAI logo

CrewAI

Use Flutterwave MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Flutterwave.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Flutterwave 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