KEGG MCP. Map Genes, Find Pathways, Check Drug Safety
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
KEGG. Query the Kyoto Encyclopedia of Genes and Genomes (KEGG) directly from your AI agent. This server gives you single-point access to biological pathways, metabolic data, and chemical compounds.
Use it to run specific queries—like finding drug-drug interactions (`kegg_ddi`) or mapping genes to pathways (`kegg_link`)—without writing boilerplate REST calls.
It’s the gold standard for querying complex genomic and systems biology data.
What your AI agents can do
Kegg conv
Converts KEGG identifiers to and from outside identifiers (e.g., NCBI, UniProt).
Kegg ddi
Finds adverse drug-drug interactions for pharmacological research.
Kegg find
Searches the database for entries matching a query keyword or chemical data.
The server finds related entries by mapping genes to metabolic or signaling pathways using kegg_link.
It searches for adverse drug-drug interactions (DDI) specifically for clinical pharmacology research via kegg_ddi.
The agent finds entries matching a query keyword or chemical data using kegg_find.
You get detailed records for genes, proteins, and organisms using kegg_get.
The server retrieves a list of entry identifiers and associated names for a given pathway or organism using kegg_list.
It handles the conversion of identifiers between KEGG and external databases like NCBI and UniProt using kegg_conv.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
KEGG MCP Server: 7 Tools for Bioinformatics
Use these seven tools to analyze identifiers, find interactions, and retrieve complex biological data directly from the KEGG database.
019e5d2akegg conv
Converts KEGG identifiers to and from outside identifiers (e.g., NCBI, UniProt).
019e5d2akegg ddi
Finds adverse drug-drug interactions for pharmacological research.
019e5d2akegg find
Searches the database for entries matching a query keyword or chemical data.
019e5d2akegg get
Retrieves detailed database entries for genes, proteins, and organisms in various file formats.
019e5d2akegg info
Displays KEGG database release information and statistics.
019e5d2akegg link
Finds related entries by mapping genes to metabolic or signaling pathways using cross-references.
019e5d2akegg list
Obtains a list of identifiers and associated names for a specific pathway or organism.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with KEGG, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're connecting your AI client directly to KEGG (Kyoto Encyclopedia of Genes and Genomes), the go-to source for biological pathways, metabolic data, and chemical compounds. This server lets you run complex genomic and systems biology queries without having to write boilerplate REST calls. You just tell your agent what you need, and it handles the rest.
You can map genes to metabolic or signaling pathways using kegg_link. You can find adverse drug-drug interactions for clinical pharmacology research with kegg_ddi. You can search the database for entries matching a query keyword or specific chemical data using kegg_find. You get detailed records for genes, proteins, and organisms in various formats using kegg_get, and you can also get a list of identifiers and associated names for a specific pathway or organism using kegg_list.
You can convert identifiers between KEGG and outside databases like NCBI and UniProt using kegg_conv. You can check the KEGG database release information and statistics with kegg_info.
How KEGG MCP Works
- 1 Subscribe to the KEGG MCP Server and configure your access credentials (if required).
- 2 Ask your AI agent a question—for example, 'What are the DDI for Drug X?'
- 3 Your agent automatically calls the correct tool (
kegg_ddi), processes the data, and presents the answer in context.
The bottom line is that your AI client handles the complex API calls and data formatting, so you just talk to the database.
Who Is KEGG MCP For?
The computational biologist who needs to cross-reference metabolic pathways and gene sequences quickly. The pharmacologist who needs to check drug safety profiles during discovery. The data scientist integrating high-quality, standardized biological metadata into an automated pipeline.
Automates the retrieval of gene sequences and pathway maps, eliminating manual REST calls and ensuring data integrity across multiple KEGG systems.
Runs specific checks, like identifying adverse drug-drug interactions (kegg_ddi), to accelerate drug safety profiling during the discovery phase.
Integrates structured biological metadata—like compound data from kegg_find—directly into analysis pipelines from the chat interface.
What Changes When You Connect
- Pathway Mapping: Instead of manually traversing links between different KEGG sections,
kegg_linkfinds related entries by mapping genes to metabolic or signaling pathways. You see the entire biological context instantly. - Drug Safety: You don't have to run multiple searches to check drug safety.
kegg_ddihandles the complex logic, identifying adverse drug-drug interactions (DDI) for clinical research. - Cross-Reference: Manually switching between NCBI, UniProt, and KEGG is a nightmare.
kegg_convhandles the ID conversion, giving you a single source of truth regardless of the external database. - Compound Discovery: When you need to search for a chemical,
kegg_findlets you query by keyword, formula, or mass, pulling compound data directly into your chat window. - Data Retrieval: Getting full gene details used to mean writing complex file-format requests. Now,
kegg_getpulls structured data on genes, proteins, and organisms in one go. - Organism Tracking: Need to know which species are covered?
kegg_listgives you a clean list of identifiers and associated names, letting you scope your research immediately.
Real-World Use Cases
Checking for drug toxicity
A pharmacologist needs to know if a new compound interacts with existing medications. They ask their agent, 'Check DDI for Compound X and Drug Y.' The agent runs kegg_ddi, returns a structured report listing all adverse interactions, solving a critical safety check immediately.
Tracing a metabolic route
A computational biologist discovers a novel gene and needs to see what metabolic pathways it belongs to. They ask their agent to map the gene. The agent uses kegg_link, which returns not just the pathway name, but the full list of related genes and cross-references, making the connection visible.
Comparing datasets
A data scientist has gene IDs from UniProt and needs to cross-reference them in KEGG. Instead of writing a custom script to map IDs, they use kegg_conv. The agent converts the UniProt list to KEGG IDs, and the data scientist can immediately integrate the structured KEGG data into their analysis pipeline.
Broad organism survey
A researcher starts a project and needs to know the scope of the KEGG database. They ask the agent to list all available organisms. The agent runs kegg_list, providing a list of thousands of available IDs (like 'hsa' or 'mmu'), instantly scoping the project's biological scope.
The Tradeoffs
Writing complex API calls
Trying to find a gene's pathway requires knowing the exact REST endpoint, required headers, and file format (/rest/gene?id=...&format=tsv). It's tedious, fragile, and requires a separate Python script just for the initial query.
→
Just ask your agent: 'What pathways is gene ABC involved in?' The agent uses kegg_link and presents the pathway map directly in the chat, skipping the entire scripting phase.
Manually converting identifiers
You pull a list of IDs from one source (e.g., NCBI) and have to write a separate script or use a lookup table to match them to KEGG IDs. This is where data integrity breaks down.
→
Use kegg_conv. Give the agent the external IDs, and it handles the conversion to KEGG IDs instantly. This keeps your data stream clean and accurate.
Over-relying on general search
Using a basic search engine to find chemical compounds means you get random academic papers, not structured data. You waste time parsing irrelevant text.
→
Use kegg_find. Query the compound database directly, specifying keywords or formulas. The agent returns structured, verifiable data records, not just links to PDFs.
When It Fits, When It Doesn't
Use this server if your core workflow involves linking biological data—specifically, mapping genes to metabolic pathways or checking drug interactions. The tools are built for high-stakes, interconnected biological analysis. You need deep data integrity and the ability to cross-reference multiple specialized databases (UniProt, NCBI, KEGG).
Don't use this if you are simply looking for general biological definitions or if your data is confined to a single, non-interconnected source. If you just need a basic definition, a general LLM is fine. But if you need to know how two genes interact, or what a compound does in a specific pathway, you need kegg_link and kegg_ddi. It’s about relationship data, not just data points.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Sifting through KEGG documentation to understand a single pathway's connections is a massive time sink.
Before this, tracing a metabolic pathway meant opening multiple browser tabs. You'd check the gene ID in one tab, find its related pathway in another, and then manually look up the compounds involved in a third. It was a painful cycle of copy-pasting IDs and bouncing between different resource pages, losing context every time.
Now, you just ask your agent: 'What are the pathways linked to gene ABC?' The agent uses `kegg_link` and dumps the full, structured pathway map right in the chat. You get the full picture instantly, without ever leaving the conversation.
KEGG MCP Server: Drug Safety and Compound Discovery
Drug discovery requires checking every possible interaction. Manually checking adverse drug-drug interactions (DDI) across multiple databases is nearly impossible to track, and the data is never consolidated.
With `kegg_ddi`, you input the drugs, and the server runs the check, providing a consolidated list of interactions and their severity. The process moves from weeks of manual database checking to a single, immediate query.
Common Questions About KEGG MCP
How do I use the `kegg_ddi` tool to find drug interactions? +
Simply ask your agent to run kegg_ddi and list the drugs you are interested in. The server finds all known adverse interactions between the specified compounds, which is crucial for clinical research.
What is the difference between `kegg_get` and `kegg_info`? +
kegg_get retrieves specific data entries (like a gene's full profile). kegg_info provides meta-data about the database itself—things like the current release version or overall statistics. Use kegg_get for content, kegg_info for context.
Can I use `kegg_conv` for multiple IDs? +
Yes. You can provide a list of external identifiers, and kegg_conv handles the bulk conversion to KEGG IDs. This is faster than converting them one by one and is necessary for bulk data analysis.
How do I find a compound using `kegg_find`? +
You ask the agent to run kegg_find and specify the compound name or formula. The tool returns multiple matching entries, giving you structured data for everything from glucose to custom glycans.
How do I use `kegg_link` to find related biological pathways? +
The kegg_link tool finds related entries using database cross-references. You provide a starting gene or pathway ID, and the tool returns all associated entries, letting you map out a full biological context.
What is the purpose of `kegg_list` for listing KEGG organisms? +
kegg_list obtains a list of entry identifiers and associated names. To see all available organisms, simply use the 'organism' option parameter.
If I get an error with `kegg_get`, what should I check? +
First, check if the ID you're passing to kegg_get is correctly formatted and exists in the KEGG database. The tool requires specific identifiers (like hsa:10458) to pull detailed records.
Can I use `kegg_conv` to convert a list of identifiers at once? +
Yes, kegg_conv handles conversions for multiple IDs. You can pass a comma-separated list of identifiers, and the tool will attempt to convert all of them simultaneously.
How can I find all metabolic pathways associated with a specific human gene? +
You can use the kegg_link tool. Specify 'pathway' as the target_db and the human gene ID (e.g., 'hsa:10458') as the source_db to retrieve all linked biological pathways.
Can I search for chemical compounds using an exact molecular mass? +
Yes! Use the kegg_find tool with the database set to 'compound', the mass value as the query, and the option set to 'exact_mass'.
Is it possible to check for interactions between multiple drugs at once? +
Absolutely. Use the kegg_ddi tool and provide the drug identifiers separated by a '+' sign (e.g., 'D00564+D00017') to find known adverse interactions.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Object Hash Engine
Generate deterministic SHA-256 fingerprints of any JSON object. Keys are automatically sorted so {b:2,a:1} and {a:1,b:2} always produce the exact same hash. Essential for deduplication.
Fauna (Serverless DB)
Execute FQL queries directly against your Fauna serverless database from any AI agent to manage collections, documents, and indexes.
Directus
Turn any SQL database into a powerful headless CMS with instant REST and GraphQL APIs for your custom content models.
You might also like
TaxBandits
File US tax forms electronically including W-2, 1099, and ACA forms with IRS-authorized e-filing and instant status tracking.
Fleetio
Manage vehicles, track maintenance, and monitor fuel entries via AI agents with Fleetio.
Zakeke
Manage customized product designs, 3D configurations, and orders via Zakeke.