EBI InterPro MCP for AI. Classify proteins down to their functional domains.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
EBI InterPro MCP connects your AI agent to the world's central resource for protein classification. This MCP allows you to classify proteins by predicting functional domains, mapping structural data, and exploring evolutionary relationships across every species.
It lets you go beyond simple sequence matching, giving deep insight into a protein's function based on its domain profile.
What your AI can do
Get cdd entry
Retrieves detailed information about a specific Conserved Domain Database (CDD) entry using an accession number.
Get clan
Gets super-family grouping details for Pfam clans, including the name and member count of the group.
Get entry
Fetches general metadata for any InterPro entry, listing its family type, GO terms, and cross-references to other databases.
Predicts and retrieves detailed information about known functional domains (like Pfam or CDD) associated with a given protein sequence.
Finds specific PDB IDs and resolutions for proteins that match an InterPro entry, connecting function to physical structure.
Determines which organisms or taxonomic groups contain a protein matching a specific domain or family. This helps map evolution across life.
Assesses how completely the proteins of an entire organism (a proteome) are annotated with known domains.
Lists every known protein in a database that shares a specific domain or family annotation, across different organisms.
Ask an AI about this
Waiting for input…
EBI InterPro: 16 Tools for Bioinformatics
These tools let you search protein families, retrieve domain details, check taxonomy, or map structures using specific accessions and keywords.
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 EBI InterPro on VinkiusGet Cdd Entry
Retrieves detailed information about a specific Conserved Domain Database (CDD) entry using an accession number.
Get Clan
Gets super-family grouping details for Pfam clans, including the name and member...
Get Entry
Fetches general metadata for any InterPro entry, listing its family type, GO terms...
Get Entry Proteins
Returns a list of all protein accessions that match a given InterPro entry across...
Get Entry Structures
Finds all PDB structures associated with an InterPro entry, giving names and...
Get Entry Taxonomy
Returns the taxonomic distribution of an InterPro entry, showing which organisms contain that specific domain or family.
Get Pfam Entry
Gets detailed information for a Pfam domain or family using its accession number (e.g., PF00069).
Get Protein
Retrieves comprehensive details for a protein, including counts of associated...
Get Protein Entries
Lists every single InterPro entry that matches a specific protein sequence, which is...
Get Proteome
Gets domain coverage statistics and basic details for an entire organism's proteome...
Get Structure
Retrieves a PDB structure file along with mapped InterPro annotations based on a...
Get Taxonomy
Returns the taxonomic node details for an organism, including its rank and counts of associated entries and proteins.
List Entry Databases
Lists all member databases supported by InterPro and shows how many total entries each one contains.
Search Entries
Searches across InterPro entries using keywords (like 'kinase') or filtering by...
Search Proteins
Searches for proteins within InterPro using a name or keyword, giving back UniProt...
Search Taxonomy
Searches the organism database by common names (like 'human') to find relevant taxon...
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 EBI InterPro, 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 InterPro. 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 connection provides 16 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking protein function requires jumping between three different websites.
Today, if a bioinformatician wants to know about a domain, they first have to find the basic entry (Site A). Then they copy that ID and paste it into the structure database (Site B) to see PDBs. Finally, they jump over to the phylogeny site (Site C) just to check which species use it. It's slow, prone to copy-paste errors, and you lose context every time.
With this MCP, your agent handles all that hand-off for you. You ask one question—like 'What are the structures and species of this kinase domain?'—and get a single, unified report combining data from multiple sources. It's instant.
Get Domain Context with InterPro
The MCP automatically pulls in the deep details you used to spend hours collecting: it gathers the domain family descriptions, lists all related UniProt proteins via `get_entry_proteins`, and even maps out the full taxonomy using `get_entry_taxonomy`.
What changes is that your analysis moves from being a tedious data assembly job to a rapid question-and-answer session. You get the answer, not a list of links.
What your AI can actually do with this
This connector gives your agent the ability to analyze proteins at a highly technical level. You can feed it a protein sequence, and it will tell you exactly what functional domains that sequence belongs to—whether those are kinase domains or something else entirely. It pulls data from a huge collection of databases like Pfam and CDD through one unified interface.
Need to know which species carry this domain? Or where the 3D structure exists in the PDB archive? The MCP finds it all. You can even check how well an entire organism's proteome is annotated for domains, giving you a full picture of its functional coverage. Because Vinkius hosts this resource, your AI client treats InterPro like a single, massive domain expert, making complex biological questions easy to ask.
019dea5f-1c50-73b3-b10e-d4312221e812 Here's how it actually works
The bottom line is, you don't have to jump between 13 different bioinformatics websites to get a full picture of a protein.
Tell your AI client what biological question you're asking—like 'What domains does this protein have?'
The MCP sends the query to InterPro and pulls data from multiple sources, consolidating domain details, structures, and species information.
Your agent receives a structured report detailing the protein's classification across various databases (Pfam, CDD) and its evolutionary context.
Who is this actually for?
Molecular biologists and bioinformaticians need this. If your job involves analyzing sequences or predicting function, you constantly run into the pain point of having to stitch together data from domain databases, structure repositories, and phylogenetic trees manually.
Uses the MCP to find PDB structures for specific protein domains, allowing them to compare 3D folds across different species.
Runs domain classification on unknown sequences to predict their function and determine if they belong to a known family (like the p53 tumor suppressor group).
Integrates protein family classifications into automated pipelines, using the MCP's ability to assess proteome coverage across entire genomes.
What Changes When You Connect
You can immediately determine a protein's domain profile by calling get_protein_entries, answering the core question: 'What domains does my protein have?'
Instead of checking multiple sites, you use list_entry_databases to see exactly how many entries are available across all 13+ member databases in one API call.
To understand evolution, run a query with get_entry_taxonomy; this tells you which organisms share that domain or family, essential for conservation studies.
When you need structural context, use get_structure to pull PDB IDs and corresponding annotations directly related to an InterPro entry. No manual database cross-referencing needed.
You can assess a whole genome's completeness by running get_proteome, which provides domain coverage statistics for the entire organism, helping pinpoint annotation gaps.
See it in action
Investigating an unknown sequence
A molecular biologist gets a novel protein sequence. Instead of guessing, they ask their agent to run get_protein_entries. The MCP returns every associated domain (Pfam, CDD), letting them immediately predict the function and family type.
Mapping functional changes across species
An evolutionary biologist wants to know if a specific kinase domain is conserved. They use get_entry_taxonomy on the relevant InterPro entry, quickly seeing which kingdoms—from archaea to mammals—contain that critical domain.
Building a functional pipeline
A bioinformatician needs to process thousands of protein sequences. They use search_proteins by name (e.g., 'insulin') to get core IDs, then run get_entry_proteins on those IDs to batch-process all associated domain assignments.
Checking database scope
A student needs to know the full scale of InterPro. They execute list_entry_databases, which immediately provides a count breakdown for every member database, proving the depth and breadth of the resource.
The honest tradeoffs
Over-relying on simple searches
Just running 'search_entries' and thinking that gives all the answers. You might get a keyword match, but you won't know if it has structural data or lineage info.
Always follow up broad searches with targeted calls. For example, after finding an entry via search_entries, run get_entry_structures and get_entry_taxonomy to get the full context.
Ignoring proteome coverage
Only checking a single protein's domain profile (get_protein) and assuming that tells you about the whole organism's function. That's usually wrong.
Always assess the bigger picture by running get_proteome first. This gives you a full view of the proteome ID and how many domains are annotated across all its proteins.
Mixing up domain searches
Using a general search when you need deep details on one specific family, like confusing search_entries with get_pfam_entry.
If you know the Pfam accession (e.g., PF00069), use get_pfam_entry. It's more direct and precise than a general search.
When It Fits, When It Doesn't
Use this MCP if your goal is comprehensive protein characterization: you need to link sequence, function, structure, and evolution in one go. You should use it when predicting domain membership or assessing the full functional breadth of an organism's proteome. Don't use it if you only need a simple list of all proteins by name—search_proteins handles that fine. But don't assume any single tool gives everything; for example, get_cdd_entry is great for CDD data, but to find the structure, you still need to call get_entry_structures. The key is combining these specialized calls into one workflow.
Questions you might have
How do I find all domains for one protein using get_protein_entries? +
You pass the UniProt accession to get_protein_entries. It returns every associated InterPro entry, giving you a complete list of its functional domain assignments.
Can I use search_taxonomy to find an organism's full profile? +
Yes. You run search_taxonomy with the name (e.g., 'human'), and then use get_taxonomy on the returned ID to get its rank, lineage, and associated protein counts.
What is the difference between get_protein and get_proteome? +
get_protein gives you domain data for a single sequence. get_proteome looks at an entire organism's ID, providing stats on how many proteins in that whole genome are annotated with domains.
How do I check if Pfam is included in the database scope? Use list_entry_databases. +
Running list_entry_databases shows you all member databases. You'll see Pfam listed there, along with its current entry count, confirming it's part of the unified resource.
When using `search_entries`, how should I filter my results to look only at domains, excluding entire families? +
You must specify the entry type parameter in search_entries. This allows you to narrow the search scope immediately. Instead of getting all related data, you limit the output strictly to domain or family types as needed for your analysis.
If I run `get_entry` for an InterPro ID, how do I use `get_entry_structures` to find its associated 3D models? +
You pass the primary InterPro accession ID into get_entry_structures. This function links the abstract annotation metadata directly to physical structural data. It returns PDB IDs and resolution details for comparison.
When I use `get_taxonomy`, how do I explore the evolutionary lineage or parent nodes of an organism? +
The get_taxonomy tool includes rank information in its results. This lets you trace ancestry and see which broader groups contain a specific species ID. It maps hierarchical relationships, essential for understanding conservation.
Can I use `get_pfam_entry` to query multiple Pfam accessions (like PF00069 and another one) in a single request? +
Yes. The tool accepts an array or comma-separated list of Pfam IDs for batch querying. This is the most efficient way to retrieve domain details for several known protein families at once.
Do I need an API key? +
No. The InterPro API is completely public and requires no authentication. Enter any placeholder value in the API key field to activate the server immediately.
What databases does InterPro integrate? +
InterPro integrates 13+ member databases including Pfam (protein families), CDD (conserved domains from NCBI), SMART (signalling domains), Prosite (patterns and profiles), PANTHER (evolutionary classification), Gene3D (structural domains from CATH), HAMAP (microbial families), PRINTS (fingerprints), PIRSF (classification system), SFLD (superfamilies), and NCBIfam. This gives you a unified view of protein domain and family annotations from the world's leading classification resources.
Can I find which organisms have a specific protein domain? +
Yes. Use the get_entry_taxonomy tool with any InterPro accession to see the taxonomic distribution of that domain or family. This shows which organisms — from bacteria to humans — contain proteins with that specific domain. It is one of the most powerful tools for evolutionary biology, revealing how protein domains have been conserved or diversified across the tree of life.
We've already built the connector for EBI InterPro. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 16 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.