How to Use the KEGG MCP in CrewAI

Q: How do I pass the KEGG MCP server to a CrewAI agent?

You can pass the Vinkius server URL directly into the mcps list when defining your CrewAI agent. This automatically grants that specific agent access to tools like keggget and kegglist without exposing them to the entire crew.

Q: Can a CrewAI researcher agent use KEGG and keggfind to search for compounds?

Yes, you can assign the keggfind tool to a specialized research agent in your CrewAI setup. The agent will autonomously query the database for chemical structures and share the findings with the rest of the crew.

Deploy specialized agent crews to run autonomous genomic research using CrewAI and KEGG.

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 CrewAI

Create your Vinkius account to connect KEGG to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Genomic Translation Pipelines with CrewAI

The `kegg_conv` tool translates gene identifiers between databases, allowing your CrewAI translation agent to pass clean data to your analysis agent. While one specialized agent handles NCBI conversions, another can focus on mapping those results to metabolic networks. This division of labor is native to CrewAI's team-based architecture. By separating translation tasks from pathway analysis, your crew processes large genomic datasets without stalling the main execution thread of the MCP server.

Autonomous Drug Interaction Auditing

The `kegg_ddi` tool checks for adverse drug-drug interactions, enabling a dedicated safety agent in your CrewAI team to audit prescriptions autonomously. The safety agent can flag risks and pass them to a moderator agent for immediate escalation. This setup lets you build autonomous clinical review loops. The crew works in the background, analyzing patient drug lists and cross-referencing them against the database without requiring human intervention.

Collaborative Pathway and Compound Discovery

The `kegg_find` tool searches for chemical compounds matching a specific keyword, which your CrewAI researcher agent can use to seed a broader literature review. Once a compound is found, a separate analyst agent can call `kegg_link` to map its metabolic pathways. This collaborative approach mimics a real research team. Your agents share memory and context, allowing them to build a complete profile of a biochemical target by combining search results with pathway mappings.

Setup guide

Set up KEGG MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke KEGG tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="KEGG Analyst",
    goal="Access and analyze KEGG data via MCP.",
    backstory="Expert analyst with direct KEGG access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent KEGG transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="KEGG Analyst",
        goal="Access and analyze KEGG data via MCP.",
        backstory="Expert analyst with direct KEGG access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent KEGG transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the Vinkius server URL directly into the `mcps` list when defining your CrewAI agent. This automatically grants that specific agent access to tools like `kegg_get` and `kegg_list` without exposing them to the entire crew.

Yes, you can assign the `kegg_find` tool to a specialized research agent in your CrewAI setup. The agent will autonomously query the database for chemical structures and share the findings with the rest of the crew.

In a hierarchical CrewAI setup, a manager agent decides which specialist agent should run tools like `kegg_link` or `kegg_conv`. The manager coordinates the tasks to ensure data is converted before pathway mapping begins.

Yes, you can use CrewAI's tool filtering to restrict access to this MCP server. For example, you can allow your safety agent to use `kegg_ddi` while blocking it from running heavy database searches.

All data transmission is secured via HTTPS directly to the Vinkius gateway, which runs the MCP server in an ephemeral sandbox. Your patient genomic profiles and drug interaction queries are processed in memory and never stored on disk.

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