Skip to main content
Glama
openpharma-org

EMBL-EBI MCP Server

by openpharma-org
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

EMBL-EBI MCP Server

Model Context Protocol (MCP) server for EMBL-EBI bioinformatics APIs — InterPro protein domains, Pfam families, protein sequence features, and taxonomy.

Features

  • Single unified tool (embl_data) with 6 methods

  • No API key required — uses public EMBL-EBI APIs

  • InterPro domain/family search and lookup

  • Pfam protein family search

  • Protein sequence feature annotation (domains, sites, regions)

  • NCBI taxonomy search

Related MCP server: mcp-uniprot

Installation

cd embl-mcp-server
npm install
npm run build

Usage

{
  "mcpServers": {
    "embl": {
      "command": "node",
      "args": ["/path/to/embl-mcp-server/build/index.js"]
    }
  }
}

Tool: embl_data

Single unified tool with multiple methods accessed via the method parameter.

Methods

1. search_interpro

Search InterPro protein families and domains.

{
  "method": "search_interpro",
  "query": "kinase",
  "limit": 10
}

Returns: accession, name, type (family/domain/repeat), description.

2. get_interpro_entry

Get full InterPro entry details.

{
  "method": "get_interpro_entry",
  "accession": "IPR000719"
}

Returns: name, type, description, GO terms, literature references.

3. get_protein_domains

Get all InterPro domains mapped to a UniProt protein.

{
  "method": "get_protein_domains",
  "uniprot_id": "P04637"
}

Returns: domain entries with positions on the protein sequence.

4. search_pfam

Search Pfam protein families.

{
  "method": "search_pfam",
  "query": "SH2 domain",
  "limit": 10
}

Returns: Pfam accession, name, type, description.

5. get_protein_features

Get all sequence features for a UniProt protein.

{
  "method": "get_protein_features",
  "uniprot_id": "P04637"
}

Returns: features array with type, description, location (begin/end), evidence.

6. search_taxonomy

Search NCBI taxonomy via EBI.

{
  "method": "search_taxonomy",
  "query": "homo sapiens",
  "limit": 5
}

Returns: taxId, scientificName, displayName.

Data Source

License

MIT

Available Tools

1 tool
embl_dataA

Access EMBL-EBI bioinformatics APIs including InterPro, Pfam, UniProt protein features, and NCBI taxonomy. Use the "method" parameter to select an operation: search_interpro, get_interpro_entry, get_protein_domains, search_pfam, get_protein_features, search_taxonomy.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of results to return (default: 10)
queryNoSearch term for search_interpro, search_pfam, or search_taxonomy
methodYesThe operation to perform
accessionNoInterPro accession (e.g., "IPR000719") for get_interpro_entry
uniprot_idNoUniProt accession (e.g., "P04637") for get_protein_domains or get_protein_features

TDQS

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits, but it only says 'access' and lists operations. It doesn't mention read-only nature, auth requirements, rate limits, or return formats, leaving users without safety or side-effect expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exactly two sentences: the first states the overall purpose, the second explains the method parameter. It is front-loaded, efficient, and contains no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema covers parameter details well, but with no output schema and no annotations, the description leaves out what users can expect in return, error behavior, or any additional context. The core operations are listed, making it minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides descriptions for all 5 parameters, including conditional usage for each method, so the schema carries the semantic weight. The description's list of method values is already present in the enum and adds no extra meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as accessing EMBL-EBI bioinformatics APIs and enumerates the specific operations (search_interpro, get_interpro_entry, get_protein_domains, search_pfam, get_protein_features, search_taxonomy), making its function distinct and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly instructs using the 'method' parameter to select an operation, which provides internal guidance. Since there are no sibling tools, it doesn't need to differentiate from alternatives, but it lacks any mention of prerequisites or scenarios where the tool should not be used.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools. The methods within the tool are clearly distinct and cover separate domains or operations.

Naming Consistency4/5

The method names follow a consistent verb_noun pattern (e.g., search_interpro, get_protein_features), but the tool name 'embl_data' is a generic noun that does not convey an action or purpose, resulting in minor inconsistency.

Tool Count2/5

With only a single tool for a wide range of bioinformatics APIs, the tool surface is too thin. The multiple methods effectively act as sub-tools, but consolidating them into one tool makes the server feel under-scoped and reduces usability.

Completeness4/5

The methods cover essential read operations (search and retrieval) for major EMBL-EBI resources like InterPro, Pfam, UniProt features, and NCBI taxonomy. Minor gaps exist (e.g., no direct method to fetch a Pfam entry by ID), but the core querying needs are addressed.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • UniProt MCP Server

    josefdc
    A
    license
    B
    quality
    D
    maintenance
    Provides seamless access to UniProtKB protein database, enabling queries for protein entries, sequences, Gene Ontology annotations, full-text search, and ID mapping across 200+ database types.
    5
    2
    MIT

  • mcp-uniprot

    pipeworx-io
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides access to UniProt protein sequence and function knowledge base, enabling search and retrieval of protein entries, proteomes, taxonomy, and feature annotations.
    13
    MIT

  • BioTrax

    SpaceSorcerer
    A
    license
    Not graded
    quality
    C
    maintenance
    Unified genomic track, peak, and sequence retrieval tool for ENCODE, ChIP-Atlas, ReMap, GEO, and SRA/ENA with unified metadata, resolved DOI/PMID provenance, and direct FASTQ download without SRA toolkit.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/openpharma-org/embl-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server