bc_get_available_ontologies

Discover available biomedical ontologies with metadata to identify relevant terminology resources for research and data integration.

Instructions

Query OLS for all available ontologies with their metadata. Use this first to discover available ontologies.

Returns: dict: Ontologies list with id, name, description, prefix, homepage, number of terms, status or error message.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Implementation Reference

src/biocontext_kb/core/ols/_get_available_ontologies.py:8-80 (handler)

The handler function that implements the logic to retrieve all available ontologies from the OLS API, paginating through results and extracting metadata. Registered as an MCP tool via @core_mcp.tool() decorator.

@core_mcp.tool()
def get_available_ontologies() -> Dict[str, Any]:
    """Query OLS for all available ontologies with their metadata. Use this first to discover available ontologies.

    Returns:
        dict: Ontologies list with id, name, description, prefix, homepage, number of terms, status or error message.
    """
    url = "https://www.ebi.ac.uk/ols4/api/v2/ontologies"

    try:
        # First request to get total count
        params = {
            "size": "100",  # OLS now limits to 100 elements per page
            "page": "0",
            "lang": "en",
        }

        response = requests.get(url, params=params)
        response.raise_for_status()

        data = response.json()

        if not data.get("elements"):
            return {"error": "No ontologies found"}

        ontologies: list[Dict[str, Any]] = []
        total_elements = data.get("totalElements", 0)
        total_pages = (total_elements + 99) // 100  # Ceiling division

        # Iterate through all pages
        for page in range(total_pages):
            params["page"] = str(page)
            response = requests.get(url, params=params)
            response.raise_for_status()

            data = response.json()

            # Extract ontology information
            page_ontologies = [
                {
                    "id": element.get("ontologyId", ""),
                    "name": element.get("label", ""),
                    "description": element.get("definition", ""),
                    "prefix": element.get("ontologyPrefix", ""),
                    "base_uri": element.get("baseUri", ""),
                    "homepage": element.get("homepage", ""),
                    "mailing_list": element.get("mailingList", ""),
                    "number_of_terms": element.get("numberOfTerms", 0),
                    "number_of_properties": element.get("numberOfProperties", 0),
                    "number_of_individuals": element.get("numberOfIndividuals", 0),
                    "last_loaded": element.get("lastLoaded", ""),
                    "status": element.get("status", ""),
                }
                for element in data.get("elements", [])
            ]

            ontologies.extend(page_ontologies)

        # Sort by ontology ID for consistency
        ontologies.sort(key=lambda x: x["id"])

        return {
            "ontologies": ontologies,
            "total_ontologies": total_elements,
            "page_info": {
                "total_pages": total_pages,
                "num_elements": len(ontologies),
            },
        }

    except requests.exceptions.RequestException as e:
        return {"error": f"Failed to fetch available ontologies: {e!s}"}

src/biocontext_kb/core/_server.py:1-6 (registration)
Defines the core_mcp FastMCP server instance named 'BC', to which all core tools including get_available_ontologies are registered via decorators.
```
from fastmcp import FastMCP

core_mcp = FastMCP(  # type: ignore
    "BC",
    instructions="Provides access to biomedical knowledge bases.",
)
```
src/biocontext_kb/app.py:34-40 (registration)
Registers the core_mcp server (containing get_available_ontologies) into the main BioContextAI MCP app with prefix 'bc' (slugify('BC')), making the tool available as 'bc_get_available_ontologies'.
```
logger.info("Setting up MCP server...")
for mcp in [core_mcp, *(await get_openapi_mcps())]:
    await mcp_app.import_server(
        mcp,
        slugify(mcp.name),
    )
logger.info("MCP server setup complete.")
```

src/biocontext_kb/core/ols/__init__.py:1-19 (helper)

Re-exports the get_available_ontologies function for convenient import in core/__init__.py.

from ._get_available_ontologies import get_available_ontologies
from ._get_cell_ontology_terms import get_cell_ontology_terms
from ._get_chebi_terms_by_chemical import get_chebi_terms_by_chemical
from ._get_efo_id_by_disease_name import get_efo_id_by_disease_name
from ._get_go_terms_by_gene import get_go_terms_by_gene
from ._get_term_details import get_term_details
from ._get_term_hierarchical_children import get_term_hierarchical_children
from ._search_ontology_terms import search_ontology_terms

__all__ = [
    "get_available_ontologies",
    "get_cell_ontology_terms",
    "get_chebi_terms_by_chemical",
    "get_efo_id_by_disease_name",
    "get_go_terms_by_gene",
    "get_term_details",
    "get_term_hierarchical_children",
    "search_ontology_terms",
]

BioContextAI Knowledgebase MCP