# How to integrate Cats MCP with Vercel AI SDK v6 ```json { "title": "How to integrate Cats MCP with Vercel AI SDK v6", "toolkit": "Cats", "toolkit_slug": "cats", "framework": "Vercel AI SDK", "framework_slug": "ai-sdk", "url": "https://composio.dev/toolkits/cats/framework/ai-sdk", "markdown_url": "https://composio.dev/toolkits/cats/framework/ai-sdk.md", "updated_at": "2026-05-12T10:05:49.695Z" } ``` ## Introduction This guide walks you through connecting Cats to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Cats agent that can show me five random cat images, list popular cat breeds with photos, find unique cat facts for trivia through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Cats account through Composio's Cats MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Cats with - [OpenAI Agents SDK](https://composio.dev/toolkits/cats/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/cats/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/cats/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/cats/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/cats/framework/codex) - [OpenClaw](https://composio.dev/toolkits/cats/framework/openclaw) - [Hermes](https://composio.dev/toolkits/cats/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/cats/framework/cli) - [Google ADK](https://composio.dev/toolkits/cats/framework/google-adk) - [LangChain](https://composio.dev/toolkits/cats/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/cats/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/cats/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/cats/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up and configure a Vercel AI SDK agent with Cats integration - Using Composio's Tool Router to dynamically load and access Cats 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 Cats MCP server, and what's possible with it? The Cats MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cats account. It provides structured and secure access to a wide collection of cat images, breed information, and fun feline facts, so your agent can fetch cat data, browse curated cat images, and pull breed details on your behalf. - Portals listing for cat resources: Instruct your agent to list and browse all available cat-related portals, making it easy to explore organized collections of cat images and data. - Metadata exploration with pagination: Have your agent efficiently page through vast cat collections, ensuring you can access just the right portal or dataset without missing a thing. - On-demand cat image discovery: Let your agent find and retrieve high-quality cat images from the API’s large, curated library—perfect for enrichment or just a dose of cuteness. - Access to detailed breed and fact data: Ask your agent to pull up detailed info on cat breeds and fun facts, making it a handy assistant for both research and entertainment. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `CATS_CREATE_FAVOURITE` | Create Favourite | Tool to save an image as a favourite to your account. Use when you want to mark a cat image as a favourite for later retrieval or filtering by user ID. | | `CATS_CREATE_VOTE` | Create Vote | Tool to vote on a cat image. Send image_id and value (1 for upvote, 0 for downvote) to register your vote. Optionally include sub_id for user tracking. | | `CATS_DELETE_FAVOURITE` | Delete Favourite | Tool to delete a favourite from your account by its ID. Use when you need to remove a previously saved favourite image from your Cat API account. | | `CATS_DELETE_IMAGE` | Delete Image | Delete an uploaded image from your account by its ID. Use this when you need to remove an image you previously uploaded to The Cat API. | | `CATS_DELETE_VOTE` | Delete Vote | Tool to delete a vote from your account by its ID. Use when you need to remove a previously submitted vote for a cat image. | | `CATS_GET_BREED` | Get Cat Breed by ID | Tool to get detailed information about a specific cat breed by its ID. Use when you need comprehensive details about a particular breed including temperament, origin, characteristics, and URLs. | | `CATS_GET_FAVOURITE` | Get Favourite by ID | Tool to retrieve a specific favourite by its unique ID. Returns full favourite details including user ID, image ID, creation timestamp, and associated image data. Use when you need to fetch a particular favourite's information or verify favourite existence. | | `CATS_GET_IMAGE` | Get Cat Image by ID | Tool to retrieve a specific cat image by its unique ID. Returns full image details including URL, dimensions, and breed information if available. Use when you need to fetch a particular image's data or verify image existence. | | `CATS_GET_IMAGE_ANALYSIS` | Get Image Analysis | Get machine learning analysis results for an uploaded image. Returns labels with confidence scores, bounding boxes for detected objects, and content moderation results from ML vendors. Note: GIF images are not supported for analysis. | | `CATS_GET_IMAGE_BREEDS` | Get Image Breeds | Tool to retrieve breed information associated with a specific cat image. Use when you need to identify which breed(s) are shown in a particular image from The Cat API. | | `CATS_GET_PORTALS` | Get Cat Breeds | Retrieves a paginated list of cat breeds from The Cat API. Returns comprehensive breed information including name, description, temperament, origin, life span, and weight. Use this to browse available cat breeds or search for specific breed information. | | `CATS_GET_VOTE` | Get Vote by ID | Retrieves a specific vote by its unique ID from The Cat API. Returns detailed vote information including the image ID, vote value, timestamp, and optional metadata like sub_id and country code. Use this when you need to fetch details about a specific vote. | | `CATS_LIST_CATEGORIES` | List Image Categories | Retrieves a list of all active image categories from The Cat API. Categories include hats, sunglasses, boxes, sinks, and more. Use category IDs when searching or filtering images by category. | | `CATS_LIST_FAVOURITES` | List Favourites | Tool to get all favourites belonging to your account. Use when you need to retrieve saved cat images, optionally filtered by sub_id. Supports pagination to browse through large collections of favourites. | | `CATS_LIST_UPLOADED_IMAGES` | List Uploaded Images | Tool to get all images uploaded to your account via /images/upload. Supports pagination and filtering by sub_id or original filename. Use this to retrieve your uploaded images, check if a file already exists, or filter by user identifiers. The API returns images in order of upload date. | | `CATS_LIST_VOTES` | List Votes | Tool to retrieve all votes you have created. Returns a paginated list of votes with image IDs, vote values, and metadata. Use this to view voting history, filter by user segment (sub_id), or analyze vote patterns. | | `CATS_SEARCH_BREEDS` | Search Cat Breeds | Search for cat breeds by name. Use the 'q' parameter with part or all of the breed name to find matching breeds. Returns breed details including temperament, origin, and characteristics. | | `CATS_SEARCH_IMAGES` | Search Cat Images | Search for random cat images with optional filters. Filter by breed availability, size, and file type. Returns an array of image objects with URLs and metadata. Use this to find cat images for display, testing, or content generation. The default behavior returns 1 random cat image. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Cats MCP server is an implementation of the Model Context Protocol that connects your AI agent to Cats. It provides structured and secure access so your agent can perform Cats operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before you begin, make sure you have: - Node.js and npm installed - A Composio account with API key - An OpenAI API key ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install required dependencies 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 ```bash npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv ``` ### 3. Set up environment variables 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 ```bash OPENAI_API_KEY=your_openai_api_key_here COMPOSIO_API_KEY=your_composio_api_key_here COMPOSIO_USER_ID=your_user_id_here ``` ### 4. Import required modules and validate environment 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 ```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, }); ``` ### 5. Create Tool Router session and initialize MCP client What's happening: - We're creating a Tool Router session that gives your agent access to Cats 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 Cats-related tools through the MCP protocol ```typescript async function main() { // Create a tool router session for the user const session = await composio.create(composioUserID!, { toolkits: ["cats"], }); const mcpUrl = session.mcp.url; ``` ### 6. Connect to MCP server and retrieve 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 Cats tools that the agent can use ```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(); ``` ### 7. Initialize conversation and CLI interface 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 ```typescript let messages: ModelMessage[] = []; console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n"); console.log( "Ask any questions related to cats, like summarize my last 5 emails, send an email, etc... :)))\n", ); const rl = readline.createInterface({ input: process.stdin, output: process.stdout, prompt: "> ", }); rl.prompt(); ``` ### 8. Handle user input and stream responses with real-time tool feedback 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 Cats 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 ```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); }); ``` ## Complete Code ```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: ["cats"], }); 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 cats, 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 Cats 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. ## How to build Cats MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/cats/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/cats/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/cats/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/cats/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/cats/framework/codex) - [OpenClaw](https://composio.dev/toolkits/cats/framework/openclaw) - [Hermes](https://composio.dev/toolkits/cats/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/cats/framework/cli) - [Google ADK](https://composio.dev/toolkits/cats/framework/google-adk) - [LangChain](https://composio.dev/toolkits/cats/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/cats/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/cats/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/cats/framework/crew-ai) ## Related Toolkits - [Youtube](https://composio.dev/toolkits/youtube) - YouTube is a leading video-sharing platform for uploading, streaming, and discovering content. It empowers creators and businesses to reach global audiences and monetize their work. - [Amara](https://composio.dev/toolkits/amara) - Amara is a collaborative platform for creating and managing subtitles and captions for videos. It helps make content accessible and multilingual for global audiences. - [Chatfai](https://composio.dev/toolkits/chatfai) - Chatfai is an AI platform that lets users talk to AI versions of fictional characters from books, movies, and games. It offers an engaging, interactive experience for fans to chat, roleplay, and explore creative dialogues. - [Cincopa](https://composio.dev/toolkits/cincopa) - Cincopa is a multimedia platform for uploading, managing, and customizing videos, images, and audio. It helps you deliver engaging media experiences with robust APIs and flexible integrations. - [Dungeon fighter online](https://composio.dev/toolkits/dungeon_fighter_online) - Dungeon Fighter Online (DFO) is an arcade-style, side-scrolling action RPG packed with dynamic combat and progression. Play solo or with friends to battle monsters, complete quests, and upgrade your characters. - [Elevenlabs](https://composio.dev/toolkits/elevenlabs) - Elevenlabs is an advanced AI voice generation platform for lifelike, multilingual speech synthesis. Perfect for creating natural voices for videos, apps, and business content in seconds. - [Elevenreader](https://composio.dev/toolkits/elevenreader) - Elevenreader is an AI-powered text-to-speech service by ElevenLabs that converts written content into lifelike audio. It enables fast, natural audio generation from any text. - [Epic games](https://composio.dev/toolkits/epic_games) - Epic Games is a leading video game publisher and digital storefront, known for Fortnite and Unreal Engine. It lets gamers access, manage, and purchase games all in one place. - [Fal.ai](https://composio.dev/toolkits/fal_ai) - Fal.ai is a generative media platform offering 600+ AI models for images, video, voice, and audio. Developers use Fal.ai for fast, scalable access to cutting-edge generative AI tools. - [Giphy](https://composio.dev/toolkits/giphy) - Giphy is the largest online library for searching and sharing GIFs and stickers. Instantly add vibrant animated content to your apps, chats, and workflows. - [Headout](https://composio.dev/toolkits/headout) - Headout is a global platform for booking travel experiences, tours, and entertainment. It helps users discover and secure activities at top destinations, all in one place. - [Imagekit io](https://composio.dev/toolkits/imagekit_io) - ImageKit.io is a cloud-based media management platform for image and video delivery. Instantly optimize, transform, and deliver visuals globally via a lightning-fast CDN. - [Listennotes](https://composio.dev/toolkits/listennotes) - Listennotes is a powerful podcast search engine with a massive global database. Discover, search, and curate podcasts from around the world in seconds. - [News api](https://composio.dev/toolkits/news_api) - News api is a REST API for searching and retrieving live news articles from across the web. Instantly access headlines, coverage, and breaking stories from thousands of sources. - [RAWG Video Games Database](https://composio.dev/toolkits/rawg_video_games_database) - RAWG Video Games Database is the largest video game discovery and info service. Instantly access comprehensive details, ratings, and release dates for thousands of games. - [Seat geek](https://composio.dev/toolkits/seat_geek) - SeatGeek is a live event platform offering APIs for concerts, sports, and theater data. Instantly access events, venues, and performers info for smarter ticketing and discovery. - [Shotstack](https://composio.dev/toolkits/shotstack) - Shotstack is a cloud platform for programmatically generating videos, images, and audio. Automate creative content production at scale with flexible RESTful APIs. - [Spotify](https://composio.dev/toolkits/spotify) - Spotify is a streaming service for music and podcasts with millions of tracks from artists worldwide. Enjoy personalized playlists, recommendations, and seamless listening across all your devices. - [Ticketmaster](https://composio.dev/toolkits/ticketmaster) - Ticketmaster is a global platform for event discovery, ticket sales, and live entertainment management. Get real-time access to events and streamline ticketing for fans and organizers. - [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Cats MCP? With a standalone Cats MCP server, the agents and LLMs can only access a fixed set of Cats tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Cats and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Vercel AI SDK v6? 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 Cats tools. ### Can I manage the permissions and scopes for Cats while using Tool Router? Yes, absolutely. You can configure which Cats scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do. ### How safe is my data with Composio Tool Router? All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Cats data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)