get_protein_info
Retrieve protein function and sequence details from UniProt by entering an accession number.
Instructions
Get protein function and sequence information from UniProt using an accession No.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| accession | Yes | UniProt Accession No. (e.g., P12345) |
Implementation Reference
- src/uniprot_mcp_server/server.py:112-166 (handler)Core handler function that fetches protein information from the UniProt API, extracts relevant fields (name, function, sequence, length, organism), implements caching, and returns a ProteinInfo dict.
async def fetch_protein_info(accession: str) -> ProteinInfo: """Fetch protein information from UniProt API with caching.""" # Check cache first cached_data = self.cache.get(accession) if cached_data: logger.info(f"Cache hit for {accession}") return cached_data logger.info(f"Fetching data for {accession}") async with httpx.AsyncClient() as client: response = await client.get( f"{API_BASE_URL}/{accession}", headers={"Accept": "application/json"}, ) response.raise_for_status() data = response.json() # Extract relevant information protein_info: ProteinInfo = { "accession": accession, "protein_name": data.get("proteinDescription", {}) .get("recommendedName", {}) .get("fullName", {}) .get("value", "Unknown"), "function": [], "sequence": "", "length": 0, "organism": "Unknown", } # Extract function information safely for comment in data.get("comments", []): if comment.get("commentType") == "FUNCTION": texts = comment.get("texts", []) if texts: protein_info["function"].extend( [text.get("value", "") for text in texts] ) # Add sequence information seq_info = data.get("sequence", {}) org_info = data.get("organism", {}) protein_info.update( { "sequence": seq_info.get("value", ""), "length": seq_info.get("length", 0), "organism": org_info.get("scientificName", "Unknown"), } ) # Cache the result self.cache.set(accession, protein_info) return protein_info - src/uniprot_mcp_server/server.py:173-183 (handler)Dispatch logic within the call_tool handler specifically for 'get_protein_info': validates input, calls fetch_protein_info, and formats response as JSON TextContent.
if name == "get_protein_info": accession = arguments.get("accession") if not accession: raise ValueError("Accession No. is required") protein_info = await fetch_protein_info(accession) return [ TextContent( type="text", text=json.dumps(protein_info, indent=2) ) ] - src/uniprot_mcp_server/server.py:79-94 (registration)Tool registration in list_tools(): defines name, description, and inputSchema for 'get_protein_info'.
name="get_protein_info", description=( "Get protein function and sequence information from UniProt " "using an accession No." ), inputSchema={ "type": "object", "properties": { "accession": { "type": "string", "description": "UniProt Accession No. (e.g., P12345)", } }, "required": ["accession"], }, ), - ProteinInfo TypedDict: schema for the output structure of protein information.
class ProteinInfo(TypedDict): """Type definition for protein information.""" accession: str protein_name: str function: list[str] sequence: str length: int organism: str - Cache class: helper utility used by fetch_protein_info for TTL-based caching of API results.
class Cache: """Simple cache implementation with TTL and max size limit.""" def __init__(self, max_size: int = 100, ttl_hours: int = 24) -> None: """Initialize cache with size and TTL limits.""" self.cache: OrderedDict[str, Tuple[Any, datetime]] = OrderedDict() self.max_size = max_size self.ttl = timedelta(hours=ttl_hours) def get(self, key: str) -> Optional[Any]: """Get a value from cache if it exists and hasn't expired.""" if key not in self.cache: return None item, timestamp = self.cache[key] if datetime.now() - timestamp > self.ttl: del self.cache[key] return None return item def set(self, key: str, value: Any) -> None: """Set a value in cache with current timestamp.""" if len(self.cache) >= self.max_size: self.cache.popitem(last=False) self.cache[key] = (value, datetime.now())