# How to integrate Bubble MCP with Vercel AI SDK v6 ```json { "title": "How to integrate Bubble MCP with Vercel AI SDK v6", "toolkit": "Bubble", "toolkit_slug": "bubble", "framework": "Vercel AI SDK", "framework_slug": "ai-sdk", "url": "https://composio.dev/toolkits/bubble/framework/ai-sdk", "markdown_url": "https://composio.dev/toolkits/bubble/framework/ai-sdk.md", "updated_at": "2026-05-12T10:04:23.724Z" } ``` ## Introduction This guide walks you through connecting Bubble to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Bubble agent that can create a new user in your bubble app, update a record in the bubble database, fetch all orders from your bubble store through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Bubble account through Composio's Bubble MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Bubble with - [OpenAI Agents SDK](https://composio.dev/toolkits/bubble/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/bubble/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/bubble/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/bubble/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/bubble/framework/codex) - [OpenClaw](https://composio.dev/toolkits/bubble/framework/openclaw) - [Hermes](https://composio.dev/toolkits/bubble/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/bubble/framework/cli) - [Google ADK](https://composio.dev/toolkits/bubble/framework/google-adk) - [LangChain](https://composio.dev/toolkits/bubble/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/bubble/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/bubble/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/bubble/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up and configure a Vercel AI SDK agent with Bubble integration - Using Composio's Tool Router to dynamically load and access Bubble 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 Bubble MCP server, and what's possible with it? The Bubble MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Bubble applications. It provides structured and secure access to your Bubble backend, so your agent can perform actions like creating and updating database entries, running workflows, fetching app data, and managing users on your behalf. - Automated database management: Your agent can create, update, or delete entries in your Bubble app’s database, streamlining data operations without manual input. - Workflow execution: Let your agent trigger workflows inside your Bubble app to automate complex business processes based on real-time prompts or events. - Dynamic data queries: Effortlessly ask your agent to fetch, filter, or search records from any data type within your Bubble app and return structured results. - User account administration: Enable your agent to create, update, or manage user profiles, permissions, and authentication flows directly in your Bubble environment. - App configuration and resource management: Allow your agent to adjust application settings, manage resources, or monitor usage metrics—keeping your Bubble project running smoothly. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `BUBBLE_DATA_BULK_CREATE_THINGS` | Bulk Create Things | Tool to bulk create multiple Things in Bubble via newline-separated JSON. Use when you need to insert many records at once. Must have Create via API permission. | | `BUBBLE_DATA_CREATE_THING` | Create Thing | Tool to create a new Thing. Use when providing a complete JSON payload to add a new record. | | `BUBBLE_DATA_DELETE_THING_BY_ID` | Delete Thing By ID | Tool to delete a Bubble Thing by its unique ID. Use when you need to remove a specific record via the Bubble Data API. | | `BUBBLE_DATA_GET_THING_BY_ID` | Get Thing By ID | Retrieves a single Thing (record) from a Bubble Data Type by its unique ID. This is a read-only operation that fetches complete details of a specific record. The response includes all custom fields defined in the Data Type, plus standard Bubble fields (_id, created_by, created_date, modified_date). Use when you need to: - Fetch details of a specific record you know the ID of - Verify a record exists - Get the latest field values for a Thing Note: Requires the Data API to be enabled in your Bubble app settings and the specific Data Type to be exposed via the API. | | `BUBBLE_DATA_PATCH_THING_BY_ID` | Patch Thing By ID | Tool to modify selected fields on a Thing by its unique ID. Use after confirming the Thing exists. | | `BUBBLE_DATA_PUT_REPLACE_THING_BY_ID` | Replace Thing by ID | Tool to replace all editable fields on a Thing by its Unique ID. Use when you need a full overwrite of a Thing's fields and reset omitted fields to default. | | `BUBBLE_FILE_DOWNLOAD` | Download File | Tool to download a file given its URL. Use when you need to retrieve file content and obtain an s3key for subsequent upload tests. | | `BUBBLE_FILE_TEMP_CREATE` | Create Temp File | Tool to upload bytes as a temporary file to Cloudflare R2 and return an S3 key. Use when you need a short-lived file reference before persisting it in a Thing. | | `BUBBLE_FILE_UPLOAD` | Upload File | Tool to upload a file to Bubble storage. Use when you need to store arbitrary files via Bubble's /fileupload endpoint. | | `BUBBLE_META_GET_SWAGGER_JSON` | Get Bubble API Swagger JSON | Tool to retrieve the auto-generated Swagger JSON for enabled APIs. Use after enabling the Swagger file in your Bubble app's API settings. | | `BUBBLE_O_AUTH_ACCESS_TOKEN` | Get OAuth Access Token | Tool to exchange an authorization code or refresh token for an OAuth2 access token. Use after obtaining an authorization code or when refreshing an expired token. | | `BUBBLE_OAUTH_AUTHORIZE` | OAuth Authorize | Tool to initiate OAuth2 authorization flow for Bubble. Use when setting up third-party login integration. Returns the URL for user-agent redirection to obtain an authorization code. | | `BUBBLE_O_AUTH_REGISTER_APP` | Bubble OAuth Register App | Tool to validate/initialize OAuth application credentials with Bubble. It performs a real call to Bubble's /oauth/authorize endpoint (or provided override) using client_id and redirect_uri to confirm connectivity and returns supplied credentials. | | `BUBBLE_WORKFLOW_TRIGGER_GET` | Trigger Bubble Workflow via GET | Trigger a Bubble API workflow using an HTTP GET request. API workflows are server-side workflows in Bubble that can be triggered externally. Use GET for simple workflows that don't require a request body (parameters passed as query strings). For workflows requiring complex data or file uploads, use the POST version instead. Before using: The workflow must be created in Bubble's workflow editor and marked as "Expose as a public API workflow". The Bubble app must have API access enabled in its subscription. | | `BUBBLE_WORKFLOW_TRIGGER_POST` | Trigger Bubble Workflow via POST | Triggers a Bubble API workflow by name using a POST request. Use this tool to execute backend workflows in your Bubble application. The workflow must be configured in your Bubble app's API Workflows section with "Expose as public API workflow" enabled. Pass any required parameters as a JSON object in the parameters field. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Bubble MCP server is an implementation of the Model Context Protocol that connects your AI agent to Bubble. It provides structured and secure access so your agent can perform Bubble 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 Bubble 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 Bubble-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: ["bubble"], }); 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 Bubble 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 bubble, 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 Bubble 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: ["bubble"], }); 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 bubble, 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 Bubble 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 Bubble MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/bubble/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/bubble/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/bubble/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/bubble/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/bubble/framework/codex) - [OpenClaw](https://composio.dev/toolkits/bubble/framework/openclaw) - [Hermes](https://composio.dev/toolkits/bubble/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/bubble/framework/cli) - [Google ADK](https://composio.dev/toolkits/bubble/framework/google-adk) - [LangChain](https://composio.dev/toolkits/bubble/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/bubble/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/bubble/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/bubble/framework/crew-ai) ## Related Toolkits - [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure. - [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms. - [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place. - [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences. - [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses. - [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure. - [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure. - [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction. - [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting. - [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache. - [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence. - [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place. - [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines. - [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure. - [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code. - [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows. - [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights. - [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews. - [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease. - [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Bubble MCP? With a standalone Bubble MCP server, the agents and LLMs can only access a fixed set of Bubble tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Bubble 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 Bubble tools. ### Can I manage the permissions and scopes for Bubble while using Tool Router? Yes, absolutely. You can configure which Bubble 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 Bubble data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)