How to Use the AntEater MCP in Vercel AI SDK

Q: How do I configure the AntEater MCP Server inside a Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the client using the HTTP transport pointing to your Vinkius endpoint. Pass the tools array from mcpClient.tools() directly into streamText and remember to call close() when the execution finishes.

Q: Does the AntEater MCP Server schema integrate natively with Vercel AI SDK tool calling?

It does. The SDK parses the JSON schema from listusers and searchactivity natively, so your LLM knows exactly when to call them without manual mapping.

Q: How is my team's Slack and email data protected?

All queries through searchactivity run in an ephemeral, zero-trust MCP sandbox. Your communication logs are processed in-memory and never cached on Vinkius disks.

Feed live AntEater team activity and shared contact logs directly into your Vercel AI SDK streaming interface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AntEater MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream active team history to your Vercel AI SDK UI

By calling `list_recent_activity`, your application exposes real-time team actions across communication channels directly to your Vercel AI SDK application. Instead of waiting for a heavy API payload to resolve, your frontend streams the raw event logs as they happen, rendering updates instantly. Users watch their feed populate line-by-line with recent Slack messages and email threads. By pairing this tool with Edge Functions, you get sub-100ms response starts without clogging your main server thread.

Instant contact lookup via streaming MCP Server tools

With the `search_contacts` tool, your streaming agent looks up shared contact records the millisecond a user starts typing. This eliminates the traditional loading spinner by piping contact details directly into the chat interface. You don't have to write custom polling logic or state managers to handle the incoming stream. Your agent handles the data flow, using `get_contact_history` to pull up previous touchpoints while keeping the UI responsive.

Live team status checks for real-time dashboards

Querying `get_user_activity` gives your application instant access to what team members are working on right now. You feed this data into your streaming UI components so managers can see active tasks without manually refreshing. When combined with `check_anteater_status`, your app verifies connection health on the fly. This means your dashboard never displays stale status indicators, keeping your team coordination loop tight.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using the HTTP transport pointing to your Vinkius endpoint. Pass the tools array from `mcpClient.tools()` directly into `streamText` and remember to call `close()` when the execution finishes.

Yes. The server runs on Vinkius's V8 sandbox, making it lightweight enough to query via `get_contact_history` from Edge environments without cold-start delays.

It does. The SDK parses the JSON schema from `list_users` and `search_activity` natively, so your LLM knows exactly when to call them without manual mapping.

Vinkius manages the authentication layer, giving you a single endpoint token. You pass this token in your client setup, and the platform handles the underlying API handshakes.

All queries through `search_activity` run in an ephemeral, zero-trust MCP sandbox. Your communication logs are processed in-memory and never cached on Vinkius disks.

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