How to Use the Freshmarketer MCP in Vercel AI SDK

Q: How do I connect Freshmarketer to Vercel AI SDK?

Install @ai-sdk/mcp and initialize your client with createMCPClient. Pass the Freshmarketer endpoint URL to the transport config. Call mcpClient.tools() and feed the result into generateText or streamText.

Q: Can Vercel AI SDK update Freshmarketer contacts?

Yes. The agent uses upsertcontact to add or modify profiles based on user prompts. It handles the API request while your frontend streams the success state to the screen.

Q: How do I trigger a Freshmarketer event from Vercel AI SDK?

The agent calls postcustomevent when a user types a specific command. You define the prompt, and the AI SDK maps the intent to the tool execution, pushing the event straight to the marketing backend.

Build live marketing dashboards where Vercel AI SDK streams Freshmarketer contact data straight into your React components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshmarketer MCP to Vercel AI SDK

Create your Vinkius account to connect Freshmarketer 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 Freshmarketer with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Freshmarketer MCP Server data to React

You want the user to see what is happening right now. Wire up `list_contacts` and `get_contact_details` through the Vercel AI SDK. The moment the agent finds a user profile, the data streams directly into your UI components without a loading spinner. It feels instant. Your internal tools can pull up marketing metrics on demand, dropping the results into a Next.js frontend as fast as the LLM generates the tool call. You stop building custom API routes and let the agent handle the data fetching.

Trigger emails from chat interfaces

Give your support reps a chat window that actually does things. When a rep asks the agent to send a receipt, it hits `send_transactional_email` on the MCP Server in the background. The user sees the confirmation render in the chat feed immediately. You can also manage lists on the fly. If a user asks to join the VIP tier, the agent fires `upsert_contact` and `create_mailing_list`. The frontend updates the moment the backend resolves the action, keeping your staff inside one unified interface.

Read marketing journeys live

Marketing operations move fast, and static dashboards lag behind. Use `list_journeys` to pull active automation states directly into your Svelte or Vue application. Your team gets real-time visibility into campaign execution without logging into another platform. You see exactly which campaigns are running. If you need to track custom triggers, `list_custom_events` drops the event schema right into your view. It is raw data turned into instant UI, giving you granular control over how marketing information is displayed.

Setup guide

Set up Freshmarketer 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 Freshmarketer 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 Freshmarketer 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 Freshmarketer. 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 Freshmarketer 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 Freshmarketer MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize your client with `createMCPClient`. Pass the Freshmarketer endpoint URL to the transport config. Call `mcpClient.tools()` and feed the result into `generateText` or `streamText`.

Yes. The agent uses `upsert_contact` to add or modify profiles based on user prompts. It handles the API request while your frontend streams the success state to the screen.

It does. The HTTP transport layer works perfectly within Vercel Edge Functions. Just ensure you close the connection with `mcpClient.close()` when the execution finishes to prevent hanging requests.

The agent calls `post_custom_event` when a user types a specific command. You define the prompt, and the AI SDK maps the intent to the tool execution, pushing the event straight to the marketing backend.

The MCP protocol routes requests through a V8 Isolate sandbox, meaning the AI client only accesses the specific email addresses and metadata required for the active prompt. No residual data stays in memory after the session closes.

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