# How to integrate Needle MCP with Vercel AI SDK v6 ```json { "title": "How to integrate Needle MCP with Vercel AI SDK v6", "toolkit": "Needle", "toolkit_slug": "needle", "framework": "Vercel AI SDK", "framework_slug": "ai-sdk", "url": "https://composio.dev/toolkits/needle/framework/ai-sdk", "markdown_url": "https://composio.dev/toolkits/needle/framework/ai-sdk.md", "updated_at": "2026-05-12T10:19:54.008Z" } ``` ## Introduction This guide walks you through connecting Needle to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Needle agent that can list all document collections i have, show stats for your 'research' collection, find files in collection uploaded this week through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Needle account through Composio's Needle MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Needle with - [OpenAI Agents SDK](https://composio.dev/toolkits/needle/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/needle/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/needle/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/needle/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/needle/framework/codex) - [OpenClaw](https://composio.dev/toolkits/needle/framework/openclaw) - [Hermes](https://composio.dev/toolkits/needle/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/needle/framework/cli) - [Google ADK](https://composio.dev/toolkits/needle/framework/google-adk) - [LangChain](https://composio.dev/toolkits/needle/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/needle/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/needle/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/needle/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up and configure a Vercel AI SDK agent with Needle integration - Using Composio's Tool Router to dynamically load and access Needle 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 Needle MCP server, and what's possible with it? The Needle MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Needle account. It provides structured and secure access to your semantic search collections, so your agent can perform actions like creating and managing collections, uploading and deleting files, retrieving collection statistics, and listing available data sources on your behalf. - Collection management and creation: Easily instruct your agent to create new semantic search collections tailored to your data needs. - File listing and retrieval: Have your agent list and retrieve all files within a specific collection, making it simple to view and organize your indexed data. - File deletion from collections: Direct your agent to remove unwanted or outdated files from any collection by specifying file IDs for cleanup and maintenance. - Collection statistics and insights: Ask your agent to fetch real-time statistics on any collection, including document counts, index size, and timestamps to monitor your data health. - Browse all available collections: Let your agent page through and present all your collections, so you can quickly access, search, or manage your data resources. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `NEEDLE_ADD_FILES_TO_COLLECTION` | Add files to a collection | Tool to add files to a collection by providing file URLs. Use when you need to add one or more files to an existing collection. URLs can be public or private (generated via the Files API). | | `NEEDLE_ADD_FILES_TO_LOCAL_CONNECTOR` | Add Files to Local Connector | Tool to add files to a local connector by providing file metadata. Use when you need to add external files to a connector using their URLs. | | `NEEDLE_CREATE_COLLECTION` | Create Collection | Tool to create a new collection. Use after confirming the collection name. | | `NEEDLE_CREATE_LOCAL_CONNECTOR` | Create Local Connector | Tool to create a local connector that monitors specified folders on a device. Use when setting up file indexing from a local machine into Needle collections. | | `NEEDLE_DELETE_FILES_FROM_COLLECTION` | Delete files from a collection | Tool to delete files from a specific collection by providing file IDs. Use after confirming valid file IDs to remove from the collection. | | `NEEDLE_DELETE_FILES_FROM_LOCAL_CONNECTOR` | Delete files from local connector | Tool to delete files from a local connector by filename or file IDs. Use when you need to remove files from a connector's local storage. | | `NEEDLE_GET_COLLECTION` | Get Collection | Tool to retrieve details for a specific collection by its ID. Use when you need to get collection metadata including name, creation date, and search query count. | | `NEEDLE_GET_COLLECTION_STATS` | Get collection stats | Tool to retrieve statistics for a specific collection by its ID. Use when you need document count, index size, and timestamps after confirming the collection exists. Zero document count is a valid response for empty collections, not an error. | | `NEEDLE_GET_FILE_DOWNLOAD_URL` | Get File Download URL | Tool to get a short-lived signed private download URL for a Needle file. Use when you need to retrieve file content but the public storage URL requires authentication. The returned URL should be used immediately as it expires quickly. | | `NEEDLE_GET_FILE_UPLOAD_URL` | Get File Upload URL | Tool to get signed URLs for uploading local files to Needle. Use when you need to upload files to a collection. The upload URLs are valid for a short time, so upload files immediately after receiving the URLs. Multiple content types can be specified to generate multiple upload URLs in a single request. | | `NEEDLE_GET_LOCAL_CONNECTOR` | Get local connector | Tool to retrieve details of a local connector by its ID. Use when you need information about a specific local connector's configuration, device details, and associated folders. | | `NEEDLE_LIST_COLLECTION_FILES` | List Collection Files | Tool to list all files within a specific collection by its ID. Returns file metadata (including file URLs) only — not document text content; fetch file URLs separately to access content. Use when you have a collection ID and need to retrieve its files. Supports pagination. | | `NEEDLE_LIST_COLLECTIONS` | List Collections | Tool to list collections. Use after authenticating with your API key to page through collections. Similar collection names can exist; always verify the correct `collection_id` from results before performing subsequent operations. | | `NEEDLE_LIST_CONNECTORS` | List Connectors | Tool to list connectors. Use to retrieve all configured connectors in your account. | | `NEEDLE_LIST_LOCAL_CONNECTORS` | List Local Connectors | Tool to list local connectors. Use to retrieve all local connectors configured in your Needle account. | | `NEEDLE_SEARCH_COLLECTION` | Search Collection | Tool to perform semantic search within a specific Needle collection and return ranked results with source references. Use when you need to retrieve relevant content from a known collection using natural language queries. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Needle MCP server is an implementation of the Model Context Protocol that connects your AI agent to Needle. It provides structured and secure access so your agent can perform Needle 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 Needle 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 Needle-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: ["needle"], }); 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 Needle 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 needle, 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 Needle 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: ["needle"], }); 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 needle, 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 Needle 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 Needle MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/needle/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/needle/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/needle/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/needle/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/needle/framework/codex) - [OpenClaw](https://composio.dev/toolkits/needle/framework/openclaw) - [Hermes](https://composio.dev/toolkits/needle/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/needle/framework/cli) - [Google ADK](https://composio.dev/toolkits/needle/framework/google-adk) - [LangChain](https://composio.dev/toolkits/needle/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/needle/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/needle/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/needle/framework/crew-ai) ## Related Toolkits - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service. - [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows. - [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow. - [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows. - [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application. - [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities. - [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization. - [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications. - [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations. - [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key. - [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient. - [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions. - [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences. - [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement. - [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team. - [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs. - [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code. - [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets. - [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Needle MCP? With a standalone Needle MCP server, the agents and LLMs can only access a fixed set of Needle tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Needle 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 Needle tools. ### Can I manage the permissions and scopes for Needle while using Tool Router? Yes, absolutely. You can configure which Needle 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 Needle data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)