KEGG MCP for AI. Query Genomic and Systemic Biological Data.
Works with every AI agent you already use
…and any MCP-compatible client








How this MCP server connects to your AI agent
KEGG connects your AI agent directly to the Kyoto Encyclopedia of Genes and Genomes (KEGG). Query complex biological data—including metabolic pathways, gene sequences, chemical compounds, and drug interactions—using natural language.
It provides the gold standard for bioinformatics exploration without manual database calls.
What AI agents can do with KEGG Automation
Kegg conv
Converts a gene or compound identifier between KEGG and external databases like NCBI.
Kegg ddi
Searches for known adverse drug-drug interactions using chemical names or IDs.
Kegg find
Queries the database to locate entries based on general keywords or specific chemical data points.
Find related entries and visualize how genes link up into larger metabolic or signaling networks.
Identify specific adverse reactions between drugs, which is critical for pharmacology research.
Fetch detailed records on genes, proteins, and associated organisms from the KEGG database.
Find entries for compounds, glycans, or drugs using keywords or specific formulas.
Convert a gene ID from one database (like NCBI) into another required format for analysis.
Ask an AI about this
Waiting for input…
What AI agents can do with KEGG with 7 Tools
These seven tools let you analyze identifiers, find drug interactions, and retrieve deep biological records directly from the KEGG database using your AI agent.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using KEGG on VinkiusKegg Conv
Converts a gene or compound identifier between KEGG and external databases like NCBI.
Kegg Ddi
Searches for known adverse drug-drug interactions using chemical names or IDs.
Kegg Find
Queries the database to locate entries based on general keywords or specific...
Kegg Get
Retrieves full, detailed records for a specified gene or pathway in various file...
Kegg Info
Displays system-level statistics and release information for the KEGG database...
Kegg Link
Identifies related biological entries by mapping cross-references between different pathway types.
Kegg List
Generates a comprehensive list of available identifiers, such as all known organisms or pathways.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
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 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ 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
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
Built on the Model Context Protocol (MCP) for 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 connection provides 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Keeping track of all biological identifiers across multiple databases is a nightmare., Solved with Vinkius AI Gateway
Today, if you find an interesting gene ID in one paper—say, from NCBI—and your analysis requires it to be mapped into a metabolic pathway tool that uses KEGG IDs, you spend time manually cross-referencing. You copy the ID, paste it somewhere else, wait for the conversion tool to run, and then hope the resulting format is compatible with the next piece of software.
With this MCP, your agent handles the headache. Instead of manual conversions, you just tell your AI client what you're working on. The system automatically uses `kegg_conv` behind the scenes to standardize that ID immediately, giving you clean data ready for pathway analysis.
Get structured metabolic pathways with KEGG MCP
Before, tracing a gene's role in a larger system meant opening multiple tabs: one for the gene details (`kegg_get`), another to find related pathways (`kegg_link`), and maybe a third just to see what organisms are involved (`kegg_list`). It’s constant switching between different data views.
Now, you ask your agent about the pathway. The system uses `kegg_link` and aggregates all that necessary cross-referencing into one clean answer. You don't navigate; you just get the final map.
What your AI can actually do with this
Need to map out a signaling cascade or check how two drugs might clash? This MCP gives your AI agent direct access to KEGG, one of the most important biological databases available. Instead of writing complex REST API calls and dealing with multiple data endpoints, you just ask your client a question about genes, pathways, or chemistry.
For example, if you're investigating novel drug targets, you can use the system to check for adverse drug-drug interactions before running any wet lab work. It handles everything from identifying basic gene identifiers to converting them across major databases like UniProt and NCBI. When your workflow hits a biological data wall—say, you need metabolic pathway details that aren't in standard literature—this MCP makes sure the information is right there for your agent to process.
Because Vinkius hosts this entire catalog of tools, connecting KEGG means all your core systems biology needs are covered from one place.
019e5d2a-8373-70db-b8ca-52af01909f7f Here's how it actually works
The bottom line is that you get highly structured, validated biological metadata returned right into your chat interface, eliminating manual API integration steps.
Connect your AI client to the KEGG MCP through Vinkius.
Ask your agent a direct question, like 'What are the metabolic pathways linked to human gene X?'
The agent uses the appropriate tool internally and returns the structured biological data directly in the conversation.
Who is this actually for?
This MCP is for computational biologists and pharmacologists who routinely cross-reference multiple massive biological databases. It’s perfect for the researcher stuck in a data loop, manually checking drug interactions or converting IDs between NCBI and KEGG.
Runs pipelines that require systematic mapping of gene sequences to metabolic pathways and needs high-quality metadata for analysis.
Checks drug candidates against known adverse interactions or validates chemical properties during early discovery stages.
Models complex biological systems, needing to cross-reference pathways and organisms rapidly without writing boilerplate API code.
What Changes When You Connect
You stop writing custom scripts to manage cross-database IDs. Use kegg_conv to automatically convert identifiers between KEGG, NCBI, and UniProt in a single chat command.
Drug safety checks become trivial. Instead of consulting multiple pharmacology manuals, call kegg_ddi to find adverse drug interactions immediately for any pair of compounds.
Instead of browsing complex web interfaces, you get structured data on demand. Use kegg_get to pull full details about a specific gene or pathway right into your analysis context.
Build out your knowledge base with precision. Run kegg_list when you need an inventory—for example, listing every known organism the database tracks for comparison.
Map entire biological systems without guessing connections. The kegg_link tool finds related entries automatically, helping trace metabolic pathways that might otherwise be missed.
See it in action
Identifying a potential drug target
A pharmacologist needs to know if Drug A and Drug B interact poorly. They prompt their agent: 'Check for interactions between X and Y.' The agent calls kegg_ddi and returns the specific adverse interaction details, saving hours of literature review.
Validating a gene sequence
A researcher finds an unknown gene ID. They use the MCP to first run kegg_list to check if the organism is supported, then call kegg_get using the ID to retrieve all associated protein and metabolic pathway data.
Mapping a novel metabolism
A systems biologist wants to see how an enzyme fits into known pathways. They use kegg_link to find related entries, then run kegg_find with the compound name to validate its inclusion in the pathway model.
Cross-referencing datasets
A data scientist has a list of gene IDs from UniProt. They use kegg_conv first to standardize those IDs into KEGG format, allowing them to then pass the clean list to kegg_get for bulk data retrieval.
The honest tradeoffs
Treating the database like a search engine
Manually pasting vague keywords into a general search tool and hoping for a clean, structured pathway map. This yields messy links and partial data.
Use kegg_get or kegg_link. For specific gene pathways, start by listing the organism with kegg_list, then use kegg_get to retrieve the full, structured record.
Forgetting cross-database compatibility
Assuming that an ID found in a journal article (e.g., an NCBI accession number) works directly in pathway analysis tools without conversion.
Always run kegg_conv first. This guarantees the identifier is correctly mapped and ready for any other KEGG tool, like finding interactions with kegg_ddi.
Overlooking system status
Building a complex analysis without verifying if the underlying database itself is up-to-date or what version of data you are actually querying.
Before starting, run kegg_info. This confirms the current database release statistics and metadata, so your results aren't based on old information.
When It Fits, When It Doesn't
Use this MCP if your work requires deep, structured biological data—think pathway mapping, drug metabolism, or genomics. The process is highly procedural; you need to confirm connections between different types of entities (genes and chemicals). Don't use it if all you need is a simple definition of a gene (a general web search works fine), or if your data set is entirely non-biological (e.g., financial records). If you are only concerned with drug interactions, kegg_ddi handles that specific task beautifully; but for mapping the entire system around it, you'll need to follow up by using tools like kegg_link and then validating the nodes with kegg_info. This MCP is your single source of truth for complex systems biology data.
Questions you might have
How do I find out what organisms are in KEGG using kegg_list? +
You run kegg_list and specify 'organism' as the parameter. This gives you a list of all available biological species tracked by the database, like Homo sapiens or Mus musculus.
Can I use kegg_ddi to check drug interactions for something not in KEGG? +
No; kegg_ddi requires compounds that are already cataloged within the KEGG system. If your compound is novel, you'll need to search for its chemical data first using kegg_find.
What do I use kegg_conv for? +
kegg_conv handles identifier translation. You pass it an ID from one system, and it reliably spits out the corresponding ID used by KEGG or other required external databases.
Does kegg_get give me all possible data formats? +
Yes. kegg_get retrieves detailed records for a gene or pathway, and it is designed to output the information in various structured file types that your agent can easily ingest.
How do I check the database status or release version using kegg_info? +
The kegg_info tool displays system metadata, including the current database release date and statistics. This confirms if you're working with the most recent dataset available for analysis.
What is the purpose of using kegg_link to find related entries? +
kegg_link finds associated data points using cross-references across different biological systems. You use it specifically when you need to map relationships, like linking a human gene to its relevant metabolic pathway.
Can I use kegg_find for chemical structures or just general keywords? +
kegg_find is flexible; it accepts multiple inputs. You can search using general keywords, specific formulas, or even molecular masses to pinpoint matching entries across various compound databases.
Does kegg_get provide raw data formats for genes and proteins? +
Yes, kegg_get retrieves comprehensive database entries in structured or flat-file formats. This allows you to pull detailed gene sequences or full protein information directly into your analysis pipeline.
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.
We've already built the connector for KEGG. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 7 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.