How to Use the Gem MCP in Vercel AI SDK

Q: How do I connect Vercel AI SDK to the Gem MCP Server?

Run npm install ai @ai-sdk/mcp. Use createMCPClient with your HTTP transport URL and pass the tools to your generation function. Always call mcpClient.close() when you finish.

Q: Can Vercel AI SDK agents read Gem custom fields?

Yes. The agent calls listcrmcustomfields to pull your specific team fields. You can render those directly in your React UI.

Q: How do I handle authentication for the Gem MCP Server?

You handle it at the transport layer. Pass an authProvider inside your createMCPClient configuration to manage OAuth or API keys securely.

Q: Can I build a frontend that triggers Gem outreach sequences?

Definitely. Your agent can read available templates via listoutreachsequences. The recruiter picks one in your UI, and the agent handles the rest.

Connect the Vercel AI SDK to the Gem MCP Server and stream candidate CRM data straight into your Next.js frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gem MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Gem Data to Vercel AI SDK

Stop making recruiters wait for API calls. When you wire up this MCP Server, your UI fetches `list_candidates` and streams the results directly to the DOM. The user sees names and emails appear instantly. You pass the tools into `streamText`. The agent grabs `get_candidate_details` and pipes the JSON right into your React components. No spinners. Just raw speed.

Live Talent Project Dashboards

Building internal dashboards usually sucks. Now your agent pulls `list_talent_projects` and populates your Svelte or Vue views in real-time. You get a live look at hiring pipelines. Need specific metrics? The agent hits `get_project_details` and updates the UI state. The frontend stays completely synced with your recruiting backend while the user watches.

Real-Time Candidate Updates

Read-only views aren't enough. Your client can fire `update_crm_candidate` or `add_candidate_note` straight from a chat interface. The recruiter types a note, and it hits the database. You handle the response via `generateText`. The agent confirms the update, and your Next.js app reflects the new state immediately. Fast, direct, and exactly what your sourcing team wants.

Setup guide

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

Run `npm install ai @ai-sdk/mcp`. Use `createMCPClient` with your HTTP transport URL and pass the tools to your generation function. Always call `mcpClient.close()` when you finish.

Yes. The agent calls `list_crm_custom_fields` to pull your specific team fields. You can render those directly in your React UI.

You handle it at the transport layer. Pass an `authProvider` inside your `createMCPClient` configuration to manage OAuth or API keys securely.

Definitely. Your agent can read available templates via `list_outreach_sequences`. The recruiter picks one in your UI, and the agent handles the rest.

Your candidate emails and LinkedIn URLs never sit in cold storage. Vercel Edge functions execute ephemerally, meaning the data passes through memory and disappears once the request ends.

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