How to Use the KEGG MCP in Vercel AI SDK

Q: Can I stream KEGG pathway diagrams directly into my Vercel AI SDK components?

Yes. Your Vercel AI SDK agent can use keggget to retrieve pathway files or image references, then stream those URLs directly to your custom React components. The UI renders the diagrams immediately without waiting for the entire text response to finish.

Q: How does the Vercel AI SDK pass credentials to the KEGG MCP server?

You configure the server URL and token inside the createMCPClient transport settings on your hosting environment. The Vercel AI SDK securely routes tool calls to the Vinkius gateway, keeping your KEGG credentials hidden from the client browser.

Q: Can Vercel AI SDK use keggfind for auto-completing chemical queries?

Absolutely. You can bind keggfind to a text input field, allowing the Vercel AI SDK to run real-time searches as users type. It returns matching chemical structures or compounds directly to the UI search results.

Build React genomics dashboards that stream live KEGG database lookups directly into your UI via 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 KEGG MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Real-Time KEGG Pathway Mapping with Vercel AI SDK

The `kegg_link` tool lets your Vercel AI SDK application fetch cross-referenced pathway data and stream the raw connections directly to your frontend. You don't have to wait for a massive JSON payload to resolve before rendering the UI. Your users see metabolic links populate in real-time as the agent finds them. By integrating this MCP server, your Edge Functions can trigger fast pathway lookups without hitting timeout limits. The raw database links feed straight into your streaming text components, keeping the interface snappy even when querying complex human genome maps.

Live Drug-Drug Interaction Warnings in UI Components

The `kegg_ddi` tool checks for adverse drug-drug interactions and sends the warning markers straight into your streaming chat interface. When a clinician types a drug pair, your Vercel AI SDK client calls this function to identify dangerous combinations instantly. You can render these critical alerts inside custom React components as they stream in. This prevents the lag typical of older REST integrations, making clinical safety warnings feel instantaneous for the end user.

On-the-Fly ID Conversions for Frontend Tables

The `kegg_conv` tool translates outside database identifiers into KEGG-specific formats right inside your streaming application. Your Vercel AI SDK agent handles NCBI or UniProt conversions on the fly, feeding the correct IDs straight into your UI rendering pipeline. This setup avoids heavy backend translation layers. The agent handles the ID mapping via the MCP server, so your interface displays clean, unified gene tables without manual data-wrangling on your client side.

Setup guide

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

You should handle rate limiting at the Edge Function level or use a caching layer before calling the MCP server. Since the Vercel AI SDK streams responses, caching the raw output of tools like `kegg_get` or `kegg_list` prevents redundant calls to the KEGG endpoints.

Yes. Your Vercel AI SDK agent can use `kegg_get` to retrieve pathway files or image references, then stream those URLs directly to your custom React components. The UI renders the diagrams immediately without waiting for the entire text response to finish.

You configure the server URL and token inside the `createMCPClient` transport settings on your hosting environment. The Vercel AI SDK securely routes tool calls to the Vinkius gateway, keeping your KEGG credentials hidden from the client browser.

Absolutely. You can bind `kegg_find` to a text input field, allowing the Vercel AI SDK to run real-time searches as users type. It returns matching chemical structures or compounds directly to the UI search results.

Yes, because Vinkius runs the server inside an ephemeral, zero-trust V8 Isolate sandbox. When your Vercel AI SDK client queries `kegg_ddi` or `kegg_get` for sensitive patient genomic data, the payloads are processed in memory and never written to persistent logs.

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