How to Use the GBIF MCP in Vercel AI SDK

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

Install ai and @ai-sdk/mcp. Initialize it with createMCPClient using the HTTP transport type and your Vinkius endpoint URL.

Q: Can Vercel AI SDK stream GBIF occurrence maps?

Yes. Call mcpClient.tools() and pass them to streamText. Your React frontend will receive the occurrence coordinates from the server as they arrive.

Q: How do I close the Vercel AI SDK connection to GBIF?

Always call mcpClient.close() when your edge function finishes. This cleans up the HTTP transport layer and prevents hanging connections.

Stream 2.4 billion biodiversity records directly into your React and Next.js apps using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GBIF MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Taxonomy Data via MCP Server

The `search_gbif_species` tool queries 2.4 billion global biodiversity records to find exact taxonomic hierarchies. You pass it a common name like "blue whale" or "oak", and it returns the full Kingdom-to-Genus classification along with occurrence counts. Vercel AI SDK takes that JSON payload and streams it straight to your user's browser. Instead of staring at a loading spinner while the API churns, your frontend renders the taxonomic tree in real-time.

Render Live Species Profiles

The `get_gbif_species` tool pulls full species details and common names using a specific GBIF key. Your agent grabs the exact biological profile without guessing at ambiguous names. This fits perfectly into a Next.js edge function. Your AI client fetches the exact profile, formats the biological traits, and pushes the text to the UI as fast as the LLM generates the response.

Map Global Observations Instantly

The `get_gbif_occurrences` tool in this MCP Server finds exactly where a species has been observed worldwide, complete with an optional two-letter ISO country code filter like US or BR. It pulls raw geographic distribution data from the Global Biodiversity Information Facility. Combine this with a mapping component in Svelte or Vue. The agent pulls the coordinates, and the Vercel AI SDK streams the location markers directly onto the user's screen as they appear in the dataset.

Setup guide

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

Install `ai` and `@ai-sdk/mcp`. Initialize it with `createMCPClient` using the HTTP transport type and your Vinkius endpoint URL.

Yes. Call `mcpClient.tools()` and pass them to `streamText`. Your React frontend will receive the occurrence coordinates from the server as they arrive.

It does. The occurrence tool accepts standard ISO 2-letter codes. You can restrict searches to specific regions like AU or GB.

Always call `mcpClient.close()` when your edge function finishes. This cleans up the HTTP transport layer and prevents hanging connections.

This server only touches public biodiversity records, taxonomy trees, and observation locations. Vinkius runs the connection inside an ephemeral V8 Isolate Sandbox. The zero-trust architecture means your API tokens and query parameters vanish the millisecond the request finishes.

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