# How to integrate Expofp MCP with Vercel AI SDK v6 ```json { "title": "How to integrate Expofp MCP with Vercel AI SDK v6", "toolkit": "Expofp", "toolkit_slug": "expofp", "framework": "Vercel AI SDK", "framework_slug": "ai-sdk", "url": "https://composio.dev/toolkits/expofp/framework/ai-sdk", "markdown_url": "https://composio.dev/toolkits/expofp/framework/ai-sdk.md", "updated_at": "2026-05-12T10:11:02.339Z" } ``` ## Introduction This guide walks you through connecting Expofp to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Expofp agent that can add new category 'workshops' to event 1023, list all extras available for expo 2048, update category #7 name to 'vip sessions' through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Expofp account through Composio's Expofp MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Expofp with - [OpenAI Agents SDK](https://composio.dev/toolkits/expofp/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/expofp/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/expofp/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/expofp/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/expofp/framework/codex) - [OpenClaw](https://composio.dev/toolkits/expofp/framework/openclaw) - [Hermes](https://composio.dev/toolkits/expofp/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/expofp/framework/cli) - [Google ADK](https://composio.dev/toolkits/expofp/framework/google-adk) - [LangChain](https://composio.dev/toolkits/expofp/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/expofp/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/expofp/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/expofp/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up and configure a Vercel AI SDK agent with Expofp integration - Using Composio's Tool Router to dynamically load and access Expofp 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 Expofp MCP server, and what's possible with it? The Expofp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Expofp account. It provides structured and secure access to your expo and floor plan data, so your agent can manage categories, list expo details, and streamline event organization tasks for you. - Seamless expo management: Instantly list all expos linked to your Expofp account, making it easy to keep track of multiple events. - Effortless category creation: Direct your agent to add new categories to any expo, supporting better organization and event structure in seconds. - Category updates and edits: Quickly update existing category names or details for any event, so your event structure always matches your latest needs. - Streamlined category removal: Have the agent remove outdated or unnecessary categories from your expos, keeping your event data clean and relevant. - Comprehensive extras listing: Retrieve all extras for a specific expo, helping you review and manage additional event options or features at a glance. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `EXPOFP_ADD_CATEGORY` | Add Category | Tool to add a new category to an expo. Use when you have both the expo event ID and a valid API token. Example: "Add category 'Keynotes' to event 2655." | | `EXPOFP_DELETE_EXHIBITOR` | Delete Exhibitor | Tool to delete an exhibitor from an expo by their ID. Use when you have the exhibitor ID and a valid API token. | | `EXPOFP_DELETE_SESSION_SPEAKERS` | Delete Session Speakers | Tool to delete session speakers by their IDs. Use when you need to remove one or more session speakers from an expo. | | `EXPOFP_DELETE_SESSION_TRACKS` | Delete Session Tracks | Tool to delete session tracks by IDs from an expo. Use when you need to remove multiple session tracks. Provide the expo ID, API token, and list of session track IDs to delete. | | `EXPOFP_GET_BULK_READ_EXHIBITORS_TEMPLATE` | Get Bulk Read Exhibitors Template | Tool to get the template structure for bulk reading exhibitors from an expo. Use when you need to understand the required format for bulk importing exhibitor data. | | `EXPOFP_GET_OFFLINE_ARCHIVE` | Get Offline Archive | Lightweight retrieval of offline archive state that never starts a build. Returns the current known ExpoOfflineState for the specified version if available, or null if not. Use when you need to check the status of an existing archive without triggering a new build. | | `EXPOFP_GET_OR_CREATE_OFFLINE_ARCHIVE` | Get or Create Offline Archive | Retrieve the offline archive state for a specific expo version. If the archive does not exist and the requested version is 'latest', the server automatically starts the creation process and returns the build state. Use this action when you need to download an expo for offline use or check the status of an ongoing archive build. The optional waitseconds parameter enables server-side polling for synchronous workflows. | | `EXPOFP_GET_SESSION_TRACKS` | Get Session Tracks | Retrieve all session tracks for a specific expo event. Session tracks are categories or themes used to organize sessions within an expo, such as "Technology", "Marketing", "Product", etc. This action returns the complete list of tracks with their IDs, names, external IDs, and color codes. Use this action when you need to categorize or filter sessions by track. Example: "Get all session tracks for expo 32971" | | `EXPOFP_LIST_ALL_EXPO_EXTRAS` | List All Expo Extras | Retrieves all extras (additional services/items) available for a specific expo event, including general extras and booth-specific extras with exhibitor details. Use this action to get a comprehensive list of purchasable extras for an event. Example: "List all extras for event 2655." | | `EXPOFP_LIST_ALL_EXPOS` | List All Expos | Retrieve all expos (events/exhibitions) accessible with the authenticated ExpoFP account. This action fetches a complete list of expos with their details including event IDs, names, descriptions, dates, time zones, locations, and status. The expo IDs returned can be used with other ExpofP actions that require an event ID parameter. No input parameters are required - the action uses the authentication token to determine which expos the user has access to. Example usage: - "List all my expos" - "Show me all available events" - "Get all expo IDs" | | `EXPOFP_LIST_CATEGORIES` | List Categories | Retrieve all categories for a specific expo event. This action fetches a complete list of categories with their IDs and names for a given expo. The category IDs returned can be used with other ExpofP actions that require a category ID parameter (e.g., updating or removing categories). Use this action when you need to see all categories configured for an expo. Example: "List all categories for event 32971" or "Show me categories for expo 2655". | | `EXPOFP_LIST_EXHIBITORS` | Bulk Read Exhibitors | Tool to bulk read exhibitors from an expo with customizable response template. This action retrieves all exhibitors from a specified expo. You can optionally provide a response template to control which fields are returned, or pass null/omit the template to receive all available exhibitor data. Use when you need to fetch exhibitor information from an expo event. The expo ID can be obtained from the List All Expos action. | | `EXPOFP_REMOVE_CATEGORY` | Remove Category | Tool to remove a category from an expo. Use when you have the category ID and a valid API token. Example: "Remove category #123." | | `EXPOFP_SET_EXHIBITOR_LOGO` | Set Exhibitor Logo | Tool to set or remove an exhibitor logo using multipart/form-data. Use when you need to upload a logo image file or provide an image URL for an exhibitor, or remove an existing logo by passing null for the image file. | | `EXPOFP_UPDATE_CATEGORY` | Update Category | Tool to update an existing category. Use when you have the category ID and a valid API token. Example: "Update category #1 name to 'Category Blue'." | | `EXPOFP_UPDATE_EXHIBITOR` | Update Exhibitor | Tool to update an existing exhibitor. Use when you have the exhibitor ID and want to modify exhibitor details. Only fields provided in the request are updated; undefined fields remain unchanged. | | `EXPOFP_UPSERT_SESSIONS` | Upsert Sessions | Tool to create or update sessions in bulk for an expo event. Sessions are upserted based on externalId if provided - existing sessions with matching externalId are updated, otherwise new sessions are created. Use this action when you need to add new sessions to an event or update existing sessions. Example: "Add a keynote session to expo 32971" or "Update session details for external ID 'session-001'." | | `EXPOFP_UPSERT_SESSION_TRACKS` | Upsert Session Tracks | Tool to create or update session tracks in bulk for an expo. Use when you need to add new tracks or modify existing ones. Provide an id in the track object to update; omit it to create new. Example: "Create a new session track called 'Workshops' with color #FF5733." | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Expofp MCP server is an implementation of the Model Context Protocol that connects your AI agent to Expofp. It provides structured and secure access so your agent can perform Expofp 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 Expofp 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 Expofp-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: ["expofp"], }); 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 Expofp 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 expofp, 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 Expofp 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: ["expofp"], }); 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 expofp, 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 Expofp 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 Expofp MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/expofp/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/expofp/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/expofp/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/expofp/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/expofp/framework/codex) - [OpenClaw](https://composio.dev/toolkits/expofp/framework/openclaw) - [Hermes](https://composio.dev/toolkits/expofp/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/expofp/framework/cli) - [Google ADK](https://composio.dev/toolkits/expofp/framework/google-adk) - [LangChain](https://composio.dev/toolkits/expofp/framework/langchain) - [Mastra AI](https://composio.dev/toolkits/expofp/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/expofp/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/expofp/framework/crew-ai) ## Related Toolkits - [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. - [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. - [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. - [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. - [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. - [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. - [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. - [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place. - [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place. - [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives. - [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions. - [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date. - [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page. - [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes. - [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights. - [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Expofp MCP? With a standalone Expofp MCP server, the agents and LLMs can only access a fixed set of Expofp tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Expofp 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 Expofp tools. ### Can I manage the permissions and scopes for Expofp while using Tool Router? Yes, absolutely. You can configure which Expofp 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 Expofp data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)