How to Use the Firefish MCP in Vercel AI SDK

Stream Firefish recruitment data directly into your UI with Vercel AI SDK. Stop waiting for spinners and start seeing live results.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firefish MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time candidate data streaming

Feed `list_candidates` and `get_candidate` results straight into your React components. The Vercel AI SDK handles the stream so your users see profiles pop up as they load. No more stale state management. Your interface updates the second the server responds, keeping the interaction feeling snappy and responsive for your recruiters.

Instant job and placement retrieval

Hook your frontend into `list_jobs` and `list_placements` to visualize hiring pipelines. You get raw data that maps perfectly to your UI components without extra middleware. Since this MCP Server works with Edge Functions, your app remains fast. Just pipe the tool output into your generation call and let the SDK handle the heavy lifting.

Direct CRM record creation

Let users trigger `create_candidate` right from your application dashboard. The SDK captures the tool response instantly, confirming the record creation without a page refresh. It keeps your workflow tight. You define the form, the AI calls the tool, and the user gets immediate confirmation that the data hit the Firefish database.

Setup guide

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

Install the MCP package and point the client to your server URL. Use `createMCPClient` to fetch the tool definitions and pass them directly into your streamText call.

Yes. It uses lightweight HTTP transports that play nice with edge environments. You won't face cold start issues or bloated dependencies.

Absolutely. Because the tools stream their results, you can bind the output to your component state. The data appears as it arrives.

Pass your credentials through the authProvider configuration in the client setup. This keeps your keys out of the client-side code.

The SDK returns a standard error object you can catch in your stream. Handle it like any other API failure in your UI logic.

Use it with your favorite AI tools

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