How to Use the KEGG MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK use KEGG to find pathways?

Your agent formulates a search query, then calls keggfind with keywords like a gene name. After getting a list of pathway IDs, it can use keggget to retrieve the full pathway data file for analysis.

Q: What's the best way to handle KEGG drug interaction alerts with the OpenAI Agents SDK?

Use keggddi to check for interactions. Then, configure a guardrail in your agent that triggers on any positive result, forcing a pause for human-in-the-loop verification before any action is taken.

Q: How do I connect my OpenAI agent to the KEGG MCP server?

You just need to instantiate the MCPServerStreamableHttp class with the server URL from Vinkius. Pass that server object into your Agent's constructor, and the tools are discovered automatically.

Build production bioinformatics agents with the OpenAI Agents SDK and get verifiable KEGG data for every action.

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 OpenAI Agents SDK

Create your Vinkius account to connect KEGG to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Drug Interactions Before Acting

An agent can use `kegg_ddi` to check for risky drug combinations. It's a simple, direct call to the KEGG database to see if two drugs have a known adverse interaction. Here’s the key part: you can use OpenAI's built-in guardrails to flag any interaction found by `kegg_ddi`. This lets you automatically pause the agent and require a manual review from a clinical pharmacist before the system proceeds.

Chain Agents on this MCP Server

Break down complex genomic research into steps. Your first agent can use `kegg_list` to get all human pathways, then use `kegg_find` to narrow down to a specific gene family. Once it has the target pathway IDs, it hands off to a second, specialized agent. That agent's only job is to use `kegg_get` and `kegg_link` to pull the detailed pathway maps and cross-referenced protein data.

Track Every ID Conversion

Your agent will constantly need to translate identifiers—from gene names to protein IDs, or drug names to compound IDs. The `kegg_conv` tool handles this directly. Because you're using the OpenAI Agents SDK, every one of these `kegg_conv` calls is logged and traced in your OpenAI dashboard. You get a full, auditable history of how your agent connected the dots, which is critical for debugging and validation.

Setup guide

Set up KEGG MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all KEGG tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives KEGG tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate KEGG tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="KEGG Agent",
            instructions="You have access to KEGG tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent formulates a search query, then calls `kegg_find` with keywords like a gene name. After getting a list of pathway IDs, it can use `kegg_get` to retrieve the full pathway data file for analysis.

Yes. When you define your agent, you can explicitly pass it a list of allowed tools. This way, you can build agents with specific roles, like one that can only read data with `kegg_get` but can't check for drug interactions.

Use `kegg_ddi` to check for interactions. Then, configure a guardrail in your agent that triggers on any positive result, forcing a pause for human-in-the-loop verification before any action is taken.

You just need to instantiate the `MCPServerStreamableHttp` class with the server URL from Vinkius. Pass that server object into your Agent's constructor, and the tools are discovered automatically.

Yes. Your queries containing gene identifiers and drug names are processed in an ephemeral Vinkius sandbox that is destroyed after your request completes. This MCP setup ensures your data isn't stored, and you also benefit from OpenAI's own platform security.

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