How to Use the Front MCP in Vercel AI SDK

Q: How do I use the Vercel AI SDK to search conversations in Front?

Pass the searchconversations tool to generateText. Your agent can then construct a search query like "is:open tag:urgent" and execute it. The results stream back into your application, perfect for building a live search interface.

Q: Can my AI agent send replies to Front using the Vercel AI SDK?

Yes. Give your agent the sendinboxreply tool. From your UI, you can collect the message body and conversation ID, then instruct the agent to send the reply. The Vercel AI SDK handles the call to the MCP server.

Q: What's the best way to list all open tickets from Front with the Vercel AI SDK?

Use the listallconversations tool and filter the results on your client, or use searchconversations with a query like "is:open". The streaming nature of the Vercel AI SDK means your UI will populate with tickets as they're fetched, not all at once.

Q: How do I check if the connection to the Front API is working?

Call the verifyapistatus tool. It's a simple health check that confirms your MCP server can reach the Front API. It's a good practice to run this when your application starts.

Build UIs that react to Front events in real-time with the Vercel AI SDK. Your agent can stream conversation data directly to the page.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Front MCP to Vercel AI SDK

Create your Vinkius account to connect Front to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Front with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Front Data into Your UI

Let your agent pull conversation history and stream it live. The AI SDK's streaming functions work directly with this MCP Server, so when you call `list_conversation_messages` or `get_conversation_details`, the data appears in your React components as it arrives. This gives your UI a responsive feel. You can build a live dashboard that populates with ticket statuses from `list_all_conversations` or displays teammate availability from `list_inbox_teammates`. The data flows from Front, through the MCP server, and into your components without a loading spinner in sight.

Act on Front Data from the Frontend

Your user can trigger actions without a page refresh. Connect a button in your UI to have an agent run `send_inbox_reply`. The user types a message, clicks send, and your agent handles the API call in the background. It's a clean way to build interactive support tools. You can also manage conversation state. Let users archive a ticket by triggering `update_conversation_status` with `status: 'archived'`. Because you're using the Vercel AI SDK, you can instantly reflect that change in the UI by re-streaming the conversation list.

Build Custom Front Dashboards with the AI SDK

Give your support team a focused view of their work. Use the AI SDK to create a custom dashboard that calls `list_shared_inboxes` and then lets them drill down into specific threads with `list_inbox_threads`. The agent does the data fetching; you just build the UI. You can even build a simple contact lookup. A text input can trigger a call to `search_conversations` to find all interactions with a specific customer. The results stream back, giving your team the context they need, fast. It all runs on the edge, so it's quick.

Setup guide

Set up Front MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Front tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Front transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Front. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Front now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Front MCP in Vercel AI SDK

Pass the `search_conversations` tool to `generateText`. Your agent can then construct a search query like `"is:open tag:urgent"` and execute it. The results stream back into your application, perfect for building a live search interface.

Yes. Give your agent the `send_inbox_reply` tool. From your UI, you can collect the message body and conversation ID, then instruct the agent to send the reply. The Vercel AI SDK handles the call to the MCP server.

Use the `list_all_conversations` tool and filter the results on your client, or use `search_conversations` with a query like `"is:open"`. The streaming nature of the Vercel AI SDK means your UI will populate with tickets as they're fetched, not all at once.

Call the `verify_api_status` tool. It's a simple health check that confirms your MCP server can reach the Front API. It's a good practice to run this when your application starts.

The server only touches Front conversation and contact data that you explicitly request. It processes things like message bodies, contact details, and inbox metadata. All connections use HTTPS, and your Vinkius token is the only credential needed, keeping your Front API key secure on the server.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript