How to Use the KEGG MCP in Mastra AI

Q: How do I register the KEGG MCP server with a Mastra AI agent?

You initialize the client using new MCPClient with the Vinkius endpoint URL and then spread the tools returned by listTools() into your Mastra AI agent configuration. The framework automatically registers tools like keggfind and keggget for your agent to use.

Q: Does Mastra AI support approval steps for KEGG drug interaction checks?

Yes, you can enable requireToolApproval on the keggddi tool within Mastra AI. This forces the agent to pause and request human validation before executing any actions based on the flagged drug interactions.

Automate complex genomic workflows by connecting Mastra AI to the KEGG database.

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 Mastra AI

Create your Vinkius account to connect KEGG 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 KEGG with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branching Workflows for Drug Interaction Analysis

The `kegg_ddi` tool identifies adverse drug-drug interactions, letting your Mastra AI workflows branch dynamically based on clinical risk. If the tool flags a high-severity interaction, Mastra can automatically trigger a notification step or halt a prescription workflow. This conditional execution is native to Mastra's workflow engine. By feeding the raw interaction data directly into your agent's decision tree, you build self-correcting clinical pipelines that handle safety checks without manual code.

Automatic Retries on Large Queries via MCP Server

The `kegg_list` tool pulls down entire indexes of organisms or pathways, which your Mastra AI agents can process using built-in exponential backoff. If the KEGG API rate-limits your request, Mastra automatically retries the tool call until the list is successfully retrieved. This makes your genomic data pipelines highly reliable. You don't have to write custom error-handling code for network blips when extracting massive pathway datasets via the MCP server.

Human-in-the-Loop Verification for Pathway Links

The `kegg_link` tool maps genomic IDs to metabolic pathways, which your Mastra AI agent can present to a researcher for manual approval before updating a database. Mastra's tool approval feature pauses the workflow until a human confirms the mapping. This prevents automated agents from propagating incorrect cross-references. You get the speed of automated KEGG mapping combined with the safety of manual clinical verification.

Setup guide

Set up KEGG 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 KEGG 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: "kegg-mcp-client",
  servers: {
    "kegg-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent KEGG 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 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 Mastra AI

You initialize the client using `new MCPClient` with the Vinkius endpoint URL and then spread the tools returned by `listTools()` into your Mastra AI agent configuration. The framework automatically registers tools like `kegg_find` and `kegg_get` for your agent to use.

Yes, you can build a multi-step Mastra AI workflow that first calls `kegg_conv` to translate gene IDs, then feeds those IDs into `kegg_get` to retrieve pathway files. The workflow engine manages the data state between these steps.

You configure Mastra AI's built-in retry and backoff strategies on the agent's tool execution block. If `kegg_link` or `kegg_info` hits a rate limit, the framework waits and retries the call automatically.

Yes, you can enable `requireToolApproval` on the `kegg_ddi` tool within Mastra AI. This forces the agent to pause and request human validation before executing any actions based on the flagged drug interactions.

Your genomic and chemical queries remain secure because Vinkius executes the MCP server in an isolated, short-lived V8 sandbox. When Mastra AI requests pathway data via `kegg_get`, the data is processed in transit and never cached or stored by Vinkius.

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