Use
COMPOSIOFOR YOU
Give Claude, Codex, or any harness secure access to 1700+ tools
CLI
One command to add tools and auth to your coding agent
Build
DEVELOPER PLATFORM
SDKs, tools, and auth for agents and backend apps
MCP GATEWAY
One managed MCP endpoint for all your tools and agents
ENTERPRISE
SSO, governance, and audit controls for deploying agents org-wide
Features
TRIGGERS
Start background agents from events across your connected apps
FIREWALLNEW
Blocks instructions hidden in tool results before your agent reads them
INSTANTNEW
Audio, video, search, browser and data tools, with no keys to manage
OPTIMIZATION
Lower cost per completed task with optimised tools and skills
FOR AGENTS
CLAUDE CODEX OPENCLAW CURSOR HERMES
BUILT FOR
OFFICE WORK SALES MARKETING PRODUCT & DESIGN CUSTOMER SUPPORT ENGINEERING HR & RECRUITING FINANCE & OPS E-COMMERCE CONTENT & MEDIA IT & SECURITY
ALL USE CASES
DOCS

How to integrate Refiner MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Refiner MCP. List all active surveys this month, fetch survey responses for nps form, and more using natural language, with authentication handled for you.

Get started for free Get a demo

Refiner

Api Key

Refiner is a customer feedback and survey platform for collecting actionable user insights. Easily analyze responses and boost engagement with targeted surveys.

10 Tools

Managed auth

Connect Refiner without auth hassles

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

Book a call

Explore the MCP Gateway

Introduction

This guide walks you through connecting Refiner to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Refiner agent that can fetch survey responses, list forms and segments, manage contacts, track events, and pull reporting data through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Refiner with

Claude Code Claude Cowork OpenAI Agents SDK Claude Agent SDK Grok Bot Codex OpenClaw Hermes Atomic Agent Google ADK LangChain Mastra AI LlamaIndex CrewAI Pydantic AI AutoGen

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Refiner integration
Using Composio's Tool Router to dynamically load and access Refiner 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 Refiner MCP server, and what's possible with it?

The Refiner MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Refiner account. It provides structured and secure access to your customer feedback and survey data, so your agent can perform actions like fetching contacts, analyzing survey responses, managing user segments, updating user data, and generating reports on your behalf.

Contact management and updates: Effortlessly retrieve, update, or delete contact records, allowing your agent to keep user data clean and up-to-date.
Survey and form discovery: Instantly list all surveys or forms in your Refiner account, filter by state, and access their configurations for deeper analysis or reporting.
Survey response retrieval and analytics: Pull in all survey responses, filter results, and generate detailed analytics or reporting to uncover actionable insights from your customer feedback.
User segmentation and targeting: Fetch and browse user segments, enabling your agent to target specific groups for outreach or further analysis based on collected data.
Event tracking and behavioral logging: Automatically record user events, associate them with contacts, and enrich feedback data for advanced behavioral analytics.

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: ["refiner"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Refiner 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 Refiner-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 Refiner 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 refiner, 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 Refiner 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 Refiner 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: ["refiner"],
  });

  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 refiner, 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 Refiner 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 Refiner action and event your agent gets out of the box.

Delete Contact

Deletes a specific contact identified by user ID or email.

Get Account Info

Retrieves Refiner account information including the subscription plan, usage counters, available limits, metric update timestamps, and per-environment usage statistics.

Get Contact

Retrieve detailed information about a specific contact using their ID, email, or UUID.

Get Contacts

Tool to retrieve a list of contacts from your Refiner account.

Get Forms

Tool to retrieve a list of forms (surveys) from your Refiner account with optional filtering and pagination.

Get Reporting

Tool to retrieve aggregated reporting data for surveys including metrics and analytics.

Get Survey Responses

Retrieves a page of survey responses with optional filtering and pagination.

Get Segments

Tool to retrieve a list of user segments from your Refiner account.

Track Event

Records a named event for a user identified by user ID or email.

Update Contact

Tool to create or update a contact's attributes or account.

FRAMEWORKS

How to build Refiner MCP Agent with another framework

Claude Code

Use Refiner MCP with Claude Code

Claude Cowork

Use Refiner MCP with Claude Cowork

OpenAI Agents SDK

Use Refiner MCP with OpenAI Agents SDK

Claude Agent SDK

Use Refiner MCP with Claude Agent SDK

Grok Bot

Use Refiner MCP with Grok Bot

Codex

Use Refiner MCP with Codex

OpenClaw

Use Refiner MCP with OpenClaw

Hermes

Use Refiner MCP with Hermes

Atomic Agent

Use Refiner MCP with Atomic Agent

Google ADK

Use Refiner MCP with Google ADK

LangChain

Use Refiner MCP with LangChain

Mastra AI

Use Refiner MCP with Mastra AI

LlamaIndex

Use Refiner MCP with LlamaIndex

CrewAI

Use Refiner MCP with CrewAI

Pydantic AI

Use Refiner MCP with Pydantic AI

AutoGen

Use Refiner MCP with AutoGen

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Firecrawl

Api Key

Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.

Tavily

Api Key

Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.

Exa

Api Key

Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows.

Serpapi

Api Key

SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.

FAQ

Frequently asked questions

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

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

Start with Refiner.It takes 30 seconds.

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

Start building

How to integrate Refiner MCP with Vercel AI SDK v6

Connect Refiner without auth hassles

Introduction

Also integrate Refiner with

TL;DR

What is Vercel AI SDK?

What is the Refiner 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 Refiner MCP Agent with another framework

Claude Code

Claude Cowork

OpenAI Agents SDK

Claude Agent SDK

Grok Bot

Codex

OpenClaw

Hermes

Atomic Agent

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Pydantic AI

AutoGen

Explore Other Toolkits

Firecrawl

Tavily

Exa

Serpapi

Frequently asked questions

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

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

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

How safe is my data with Composio Tool Router?

Start with Refiner.It takes 30 seconds.