How to Use the UniProt MCP in Mastra AI

Q: How do I find isoforms using UniProt and Mastra AI?

You use searchuniprotgene. This tool provides all protein isoforms and their functional annotations for a specific gene. The workflow engine ensures this step completes successfully.

Q: What if my initial search fails? Does UniProt work with Mastra AI?

Yes, it does. If the searchuniprot call fails (for instance), Mastra AI's automatic retries kick in, giving your workflow a second shot without you writing complex error handling code.

Q: How can I get full protein details on UniProt using Mastra AI?

You call getuniprotprotein with the accession ID. This is usually the final step in a multi-stage workflow, pulling all necessary data into your process.

Q: Does the MCP Server support multiple types of UniProt data?

Absolutely. The server lets you search by name (searchuniprot), check gene isoforms (searchuniprotgene), or get a single record (getuniprotprotein). It covers three main use cases.

Build complex UniProt workflows with Mastra AI's resilient MCP Server framework.

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 Mastra AI

Create your Vinkius account to connect UniProt to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Retrieve single protein data using the MCP Server

Need deep details on one specific protein? The `get_uniprot_protein` tool handles this by taking a UniProt accession ID. It gives you the full, comprehensive record needed for your next step in a workflow. Mastra AI's built-in retry logic means if the initial request fails—maybe due to rate limits—it automatically tries again until it gets the protein data you need.

Search UniProt and manage complex biological workflows

The `search_uniprot` tool lets your agent search by name, function, or keyword. It returns key metadata like gene names, organism, subcellular location, and the sequence itself. This is ideal for multi-step processes. Because Mastra AI handles failure gracefully, you can chain multiple searches—first find the protein via `search_uniprot`, then use that data to trigger another action.

Find all isoforms with UniProt and Mastra AI

When you need to track down every variation of a protein, use `search_uniprot_gene`. This tool maps out all possible isoforms and their functional annotations for a given gene name. It’s meticulous work. This structured output is perfect for complex workflows where knowing the full genetic scope—and handling failure if one step fails—is non-negotiable.

Setup guide

Set up UniProt MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All UniProt tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "uniprot-mcp-client",
  servers: {
    "uniprot-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "UniProt Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to UniProt tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent UniProt transactions"
);
console.log(result.text);

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 Mastra AI

You use `search_uniprot_gene`. This tool provides all protein isoforms and their functional annotations for a specific gene. The workflow engine ensures this step completes successfully.

Yes, it does. If the `search_uniprot` call fails (for instance), Mastra AI's automatic retries kick in, giving your workflow a second shot without you writing complex error handling code.

You call `get_uniprot_protein` with the accession ID. This is usually the final step in a multi-stage workflow, pulling all necessary data into your process.

This MCP Server touches public biological reference data, including protein sequences and functional annotations. You aren't touching any private user details here.

Absolutely. The server lets you search by name (`search_uniprot`), check gene isoforms (`search_uniprot_gene`), or get a single record (`get_uniprot_protein`). It covers three main use cases.

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