How to Use the UniProt MCP in Vercel AI SDK

Q: How do I search UniProt using the UniProt and Vercel AI SDK?

You use the searchuniprot tool. Just pass in a name or function keyword, like 'hemoglobin'. Your AI client handles the query, returning structured data for protein names, genes, and functions.

Q: If I need isoforms, how does UniProt work with Vercel AI SDK?

The searchuniprotgene tool is what you want. It finds all protein isoforms linked to a specific gene name. This lets your agent provide comprehensive data that goes beyond the primary sequence.

Q: Can I get full details on a single UniProt entry using Vercel AI SDK?

Yep. Use the getuniprotprotein tool. You provide the accession ID, and the system returns all available data points for that specific protein record.

Q: How do I use UniProt with Vercel AI SDK in a production environment?

You call mcpClient.tools() to expose the MCP Server's tools. The streaming nature of the client is key; it lets your agent work live, which is perfect for user-facing data visualization.

Real-time UniProt data streaming into your React/Next.js app using 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 UniProt MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch specific protein details with the MCP Server

Need full info on a single protein? The `get_uniprot_protein` tool grabs all necessary details just by running the UniProt accession ID. This means your client fetches complete records, not just partial snippets. You can integrate this directly into a Next.js page. Your AI client streams the data to the UI immediately; the user sees the protein information appear live, ditching that boring loading spinner.

Search proteins across databases with Vercel AI SDK

Searching for proteins is simple using `search_uniprot`. You just pass in a keyword—like 'insulin' or 'spike protein'—and the system returns the name, gene, organism, function, and sequence. It’s quick and covers a lot of ground. This functionality lets your agent perform broad biological searches. When paired with streaming text, you can show users exactly which records are being found as they appear, making the whole process feel snappy.

Identify isoforms using UniProt via MCP Server

The `search_uniprot_gene` tool lets you find proteins encoded by a specific gene. It returns all possible protein isoforms and their functional annotations, giving you deep context on the genetics involved. You're looking past just one sequence. Use this when your user needs to know every variation of a protein linked to a known gene name. This specificity is perfect for complex biological tools built with Vercel AI SDK.

Setup guide

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

You use the `search_uniprot` tool. Just pass in a name or function keyword, like 'hemoglobin'. Your AI client handles the query, returning structured data for protein names, genes, and functions.

The `search_uniprot_gene` tool is what you want. It finds all protein isoforms linked to a specific gene name. This lets your agent provide comprehensive data that goes beyond the primary sequence.

This MCP Server touches public biological reference data, specifically protein sequences and functional annotations. It doesn't handle any private user credentials or personally identifiable information.

Yep. Use the `get_uniprot_protein` tool. You provide the accession ID, and the system returns all available data points for that specific protein record.

You call `mcpClient.tools()` to expose the MCP Server's tools. The streaming nature of the client is key; it lets your agent work live, which is perfect for user-facing data visualization.

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