How to Use the KEGG MCP in Google ADK

Q: What's the process for checking drug interactions from KEGG in a Google ADK pipeline?

The agent simply calls the keggddi tool with two drug names. The response indicates if an interaction is known, and you can build your agent's logic on Google Cloud to flag these for review.

Run large-scale genomic analysis on Google Cloud by connecting your Google ADK agent to live KEGG data.

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 Google ADK

Create your Vinkius account to connect KEGG to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query BigQuery, Map in KEGG

Pull a massive list of gene identifiers directly from your BigQuery tables. Your Gemini-powered agent can hold that entire list in its context. Then, the agent can iterate through the list, making targeted calls to `kegg_link` and `kegg_get` to map all associated pathways. It's a straight shot from your enterprise data warehouse to deep biological insight.

Find Compounds at Scale

Don't just search with keywords. Your agent can read raw chemical data—like a MOL file—from a Google Cloud Storage bucket and feed it directly to the `kegg_find` tool. KEGG then searches for compounds with similar chemical structures. This turns your agent into a powerful discovery tool that connects your proprietary data with a massive public chemical database.

Control Your Agent's Scope on this MCP Server

You don't always want your agent to have access to everything. The Google ADK lets you use a `tool_names` filter when you set up the MCP toolset. This means you can easily create a specialized safety agent for your Vertex AI pipeline that can only access `kegg_ddi` and `kegg_info`. It can check for drug interactions but can't retrieve unrelated pathway data.

Setup guide

Set up KEGG MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with KEGG tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="KEGG_agent",
    model="gemini-2.0-flash",
    instruction="You have access to KEGG tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Your agent can query BigQuery for a list of identifiers, then use Gemini's large context to reason about the entire set while making calls to KEGG tools like `kegg_get` to fetch related data for each item.

Absolutely. The combination of Gemini's 1M+ token context window and the `kegg_list` tool means your agent can get a list of thousands of genes and then intelligently decide which ones to investigate further.

The agent simply calls the `kegg_ddi` tool with two drug names. The response indicates if an interaction is known, and you can build your agent's logic on Google Cloud to flag these for review.

Yes, it's designed for it. You add the Vinkius MCP server as a toolset in your agent definition, and it works alongside your other Google Cloud tools and data sources.

Your query data, like compound identifiers or database cross-references, is sent to a zero-trust Vinkius instance for execution. That instance is temporary and doesn't persist your data, while the entire process is governed by your project's Google Cloud IAM policies.

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