# How to integrate Ntfy MCP with Vercel AI SDK v6 ```json { "title": "How to integrate Ntfy MCP with Vercel AI SDK v6", "toolkit": "Ntfy", "toolkit_slug": "ntfy", "framework": "Vercel AI SDK", "framework_slug": "ai-sdk", "url": "https://composio.dev/toolkits/ntfy/framework/ai-sdk", "markdown_url": "https://composio.dev/toolkits/ntfy/framework/ai-sdk.md", "updated_at": "2026-03-29T06:43:41.259Z" } ``` ## Introduction This guide walks you through connecting Ntfy to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Ntfy agent that can send push notification for build failures, notify me of high-priority alerts, broadcast message to all devices through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Ntfy account through Composio's Ntfy MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Ntfy with - [ChatGPT](https://composio.dev/toolkits/ntfy/framework/chatgpt) - [Antigravity](https://composio.dev/toolkits/ntfy/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/ntfy/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/ntfy/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/ntfy/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/ntfy/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/ntfy/framework/codex) - [Cursor](https://composio.dev/toolkits/ntfy/framework/cursor) - [VS Code](https://composio.dev/toolkits/ntfy/framework/vscode) - [OpenCode](https://composio.dev/toolkits/ntfy/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/ntfy/framework/openclaw) - [Hermes](https://composio.dev/toolkits/ntfy/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/ntfy/framework/cli) - [Google ADK](https://composio.dev/toolkits/ntfy/framework/google-adk) - [LangChain](https://composio.dev/toolkits/ntfy/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/ntfy/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/ntfy/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/ntfy/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up and configure a Vercel AI SDK agent with Ntfy integration - Using Composio's Tool Router to dynamically load and access Ntfy 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 Ntfy MCP server, and what's possible with it? The Ntfy MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ntfy account. It provides structured and secure access so your agent can perform Ntfy operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `NTFY_CREATE_ACCOUNT` | Create NTFY Account | Tool to register a new user account on ntfy. Use when you need to create a new user account on the ntfy.sh hosted service. Note: This endpoint is not available on self-hosted instances unless signup is explicitly enabled in the server configuration. | | `NTFY_CREATE_WEBPUSH_SUBSCRIPTION` | Create Web Push Subscription | Tool to register a web push subscription for browser notifications. Use when you need to enable push notifications from ntfy topics through a browser's native push notification system. | | `NTFY_DELETE_WEBPUSH_SUBSCRIPTION` | Delete Web Push Subscription | Tool to unregister a web push subscription from the ntfy server. Use when you need to remove browser push notifications for a previously registered endpoint. | | `NTFY_FETCH_CACHED_MESSAGES` | Fetch Cached Messages | Tool to fetch cached messages from a ntfy topic. Use when you need to retrieve previously sent messages stored on the server. Supports filtering by time (duration or timestamp), message ID, content, title, priority, and tags. Set poll=1 to return immediately after fetching available cached messages. | | `NTFY_FETCH_LATEST_MESSAGE_FROM_TOPIC` | Fetch Latest Message from Topic | Tool to fetch the most recent message from a topic's cache. Use when you need to retrieve the latest message without subscribing to the topic stream. | | `NTFY_FETCH_SCHEDULED_MESSAGES` | Fetch Scheduled Messages | Tool to fetch messages scheduled for later delivery from a topic. Use when you need to retrieve messages that are set to be delivered at a future date. The poll=1 and scheduled=1 parameters are automatically set to retrieve cached scheduled messages in a single request. | | `NTFY_GET_ACCOUNT_INFORMATION` | Get Account Information | Tool to retrieve account data for authenticated user or anonymous user. Use when you need to get account information, limits, statistics, or tier details. | | `NTFY_GET_SERVER_STATISTICS` | Get Server Statistics | Tool to retrieve server statistics including message counts and publishing rates. Use when you need to monitor ntfy server activity and get metrics about message volume. | | `NTFY_GET_SERVICE_TIERS` | Get Service Tiers | Tool to list all available ntfy service tiers with their limits and features. Use when you need to retrieve subscription tier information including pricing and usage limits. Requires that payments are enabled on the server. | | `NTFY_GET_FILE_ATTACHMENT_METADATA` | Get File Attachment Metadata | Tool to get file attachment metadata from a message without downloading the file content. Use when you need to check file size, content type, or verify file existence in the ntfy attachment cache. | | `NTFY_CHECK_NTFY_SERVICE_HEALTH` | Check NTFY Service Health | Tool to check the health status of the ntfy service. Use when you need to verify if the ntfy service is operational and responding correctly. | | `NTFY_POLL_MESSAGES_FROM_TOPIC` | Poll Messages from Topic | Tool to poll for messages from an ntfy topic without maintaining a long-standing connection. Use when you need to retrieve cached messages and have the connection close immediately after delivery. The connection ends after reading all available messages matching the criteria. | | `NTFY_PUBLISH_MESSAGE_AS_JSON_TO_NTFY` | Publish Message as JSON to NTFY | Tool to publish messages as JSON to ntfy. Use when you need to send notifications with all parameters in the request body, especially useful for integrations that cannot add custom headers. | | `NTFY_PUBLISH_MESSAGE_TO_TOPIC` | Publish Message to Topic | Tool to publish a message to a ntfy topic. Use when you need to send notifications or alerts to a topic. Topics are created dynamically if they don't exist. | | `NTFY_PUBLISH_MESSAGE_TO_TOPIC_PUT` | Publish Message to Topic (PUT) | Tool to publish a message to a topic using PUT method. Use when you need to send notifications to subscribers of a topic. Supports various options like priority, tags, attachments, and scheduled delivery. | | `NTFY_PUBLISH_MESSAGE_VIA_GET` | Publish Message via GET | Tool to publish messages to ntfy via GET request with URL parameters. Use when PUT/POST methods are unavailable or for simple webhook integration. Supports all message parameters as query strings. Without parameters, sends 'triggered' as message. | | `NTFY_SEND_MESSAGE_VIA_WEBHOOK` | Send Message via Webhook | Tool to send messages via webhook endpoint using simple GET request. Use when you need a simple webhook-style integration or for clients with limited HTTP support. | | `NTFY_SUBSCRIBE_TO_NTFY_TOPIC_WITH_FILTERS` | Subscribe to NTFY Topic with Filters | Tool to subscribe to a ntfy topic with filters based on message fields (id, message, title, priority, tags). Use when you need to retrieve specific messages from a topic using filter criteria. Returns matching messages from the topic as a JSON stream. | | `NTFY_SUBSCRIBE_TO_TOPIC_JSON_STREAM` | Subscribe to Topic (JSON Stream) | Tool to subscribe to a ntfy topic and receive messages as JSON stream. Use when you need to retrieve cached messages from a topic. The action polls the topic and returns immediately with cached messages. | | `NTFY_SUBSCRIBE_TO_MULTIPLE_NTFY_TOPICS` | Subscribe to Multiple NTFY Topics | Tool to subscribe to multiple ntfy topics simultaneously using comma-separated topic list. Use when you need to receive messages from multiple topics in a single API call. Returns cached messages when used with poll=true parameter. | | `NTFY_SUBSCRIBE_TO_TOPIC_RAW_STREAM` | Subscribe to Topic (Raw Stream) | Tool to subscribe to a topic and receive message bodies as raw text stream. Use when you need to retrieve messages without metadata like priority, tags, or titles. Each line in the response contains only the message body. Empty lines represent keepalive messages. In streaming mode, the connection remains open to receive new messages. With poll=1, cached messages are returned and the connection closes. | | `NTFY_TRIGGER_NTFY_WEBHOOK` | Trigger NTFY Webhook | Tool to trigger a webhook to publish a message to an ntfy topic via simple HTTP GET request. Use when you need to send notifications through webhooks without requiring a POST body. Sends a default 'triggered' message if no custom message is provided. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Ntfy MCP server is an implementation of the Model Context Protocol that connects your AI agent to Ntfy. It provides structured and secure access so your agent can perform Ntfy 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 Ntfy 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 Ntfy-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: ["ntfy"], }); 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 Ntfy 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 ntfy, 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 Ntfy 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: ["ntfy"], }); 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 ntfy, 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 Ntfy 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 Ntfy MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/ntfy/framework/chatgpt) - [Antigravity](https://composio.dev/toolkits/ntfy/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/ntfy/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/ntfy/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/ntfy/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/ntfy/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/ntfy/framework/codex) - [Cursor](https://composio.dev/toolkits/ntfy/framework/cursor) - [VS Code](https://composio.dev/toolkits/ntfy/framework/vscode) - [OpenCode](https://composio.dev/toolkits/ntfy/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/ntfy/framework/openclaw) - [Hermes](https://composio.dev/toolkits/ntfy/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/ntfy/framework/cli) - [Google ADK](https://composio.dev/toolkits/ntfy/framework/google-adk) - [LangChain](https://composio.dev/toolkits/ntfy/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/ntfy/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/ntfy/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/ntfy/framework/crew-ai) ## Related Toolkits - [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. - [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management. - [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly. - [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place. - [Slack](https://composio.dev/toolkits/slack) - Slack is a channel-based messaging platform for teams and organizations. It helps people collaborate in real time, share files, and connect all their tools in one place. - [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations. - [Gong](https://composio.dev/toolkits/gong) - Gong is a platform for video meetings, call recording, and team collaboration. It helps teams capture conversations, analyze calls, and turn insights into action. - [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals. - [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem. - [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity. - [Microsoft teams](https://composio.dev/toolkits/microsoft_teams) - Microsoft Teams is a collaboration platform that combines chat, meetings, and file sharing within Microsoft 365. It keeps distributed teams connected and productive through seamless virtual communication. - [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently. - [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place. - [Slackbot](https://composio.dev/toolkits/slackbot) - Slackbot is a conversational automation tool for Slack that handles reminders, notifications, and automated responses. It boosts team productivity by streamlining onboarding, answering FAQs, and managing timely alerts—all right inside Slack. - [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time. - [2chat](https://composio.dev/toolkits/_2chat) - 2chat is an API platform for WhatsApp and multichannel text messaging. It streamlines chat automation, group management, and real-time messaging for developers. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Agent mail](https://composio.dev/toolkits/agent_mail) - Agent mail provides AI agents with dedicated email inboxes for sending, receiving, and managing emails. It empowers agents to communicate autonomously with people, services, and other agents—no human intervention needed. - [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place. - [Apilio](https://composio.dev/toolkits/apilio) - Apilio is a home automation platform that lets you connect and control smart devices from different brands. It helps you build flexible automations with complex conditions, schedules, and integrations. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Ntfy MCP? With a standalone Ntfy MCP server, the agents and LLMs can only access a fixed set of Ntfy tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Ntfy 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 Ntfy tools. ### Can I manage the permissions and scopes for Ntfy while using Tool Router? Yes, absolutely. You can configure which Ntfy 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 Ntfy data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)