cBioPortal MCP Server

Instructions

Implementation Reference

• cbioportal_mcp/server.py:240-248 (handler)

  MCP tool handler for get_multiple_genes, delegates to GenesEndpoints implementation.
  async def get_multiple_genes( self, gene_ids: List[str], gene_id_type: str = "ENTREZ_GENE_ID", projection: str = "SUMMARY", ) -> Dict: """Get information about multiple genes concurrently.""" return await self.genes.get_multiple_genes(gene_ids, gene_id_type, projection)
• cbioportal_mcp/endpoints/genes.py:127-214 (helper)

  Core implementation of get_multiple_genes using concurrent batch fetches to the cBioPortal genes/fetch endpoint, with error handling, batching, and metadata.
  async def get_multiple_genes( self, gene_ids: List[str], gene_id_type: str = "ENTREZ_GENE_ID", projection: str = "SUMMARY", ) -> Dict: """ Get information about multiple genes concurrently. This method uses concurrency to fetch multiple genes in parallel, which is much more efficient than sequential requests for large batches. Args: gene_ids: List of gene IDs (Entrez IDs or Hugo symbols) gene_id_type: Type of gene ID provided (ENTREZ_GENE_ID or HUGO_GENE_SYMBOL) projection: Level of detail to return (ID, SUMMARY, DETAILED) Returns: Dictionary with gene information and performance metadata """ overall_start_time = time.time() # Single start time for the whole operation if not gene_ids: return { "genes": {}, "metadata": { "count": 0, "total_requested": 0, "errors": 0, "concurrent": True, "batches": 0, "execution_time": round(time.time() - overall_start_time, 3), }, } # For large gene lists, break into smaller batches for API compatibility batch_size = ( self.config.get("api.batch_size.genes", 100) if self.config else 100 # Default to 100 if no config provided ) gene_batches = [ gene_ids[i : i + batch_size] for i in range(0, len(gene_ids), batch_size) ] async def fetch_gene_batch(batch): try: params = {"geneIdType": gene_id_type, "projection": projection} batch_data = await self.api_client.make_api_request( "genes/fetch", method="POST", params=params, json_data=batch ) return {"data": batch_data, "success": True} except Exception as e: return {"error": str(e), "success": False} # Create tasks for all batches and run them concurrently tasks = [fetch_gene_batch(batch) for batch in gene_batches] batch_results = await asyncio.gather(*tasks) # Process results all_genes = [] error_count = 0 for result in batch_results: if result["success"]: all_genes.extend(result["data"]) else: error_count += 1 # Convert to dictionary for easier lookup genes_dict = {} key_field = ( "hugoGeneSymbol" if gene_id_type == "HUGO_GENE_SYMBOL" else "entrezGeneId" ) for gene in all_genes: gene_key_value = gene.get(key_field) if gene_key_value: genes_dict[str(gene_key_value)] = gene return { "genes": genes_dict, "metadata": { "count": len(genes_dict), "total_requested": len(gene_ids), "errors": error_count, "execution_time": round(time.time() - overall_start_time, 3), "concurrent": True, "batches": len(gene_batches), }, }
• cbioportal_mcp/server.py:96-131 (registration)

  Tool registration method that includes 'get_multiple_genes' in the tool_methods list and registers it with FastMCP via self.mcp.add_tool.
  def _register_tools(self): """Register tool methods as MCP tools.""" # List of methods to register as tools (explicitly defined) tool_methods = [ # Pagination utilities "paginate_results", "collect_all_results", # Studies endpoints "get_cancer_studies", "get_cancer_types", "search_studies", "get_study_details", "get_multiple_studies", # Genes endpoints "search_genes", "get_genes", "get_multiple_genes", "get_mutations_in_gene", # Samples endpoints "get_samples_in_study", "get_sample_list_id", # Molecular profiles endpoints "get_molecular_profiles", "get_clinical_data", "get_gene_panels_for_study", "get_gene_panel_details", ] for method_name in tool_methods: if hasattr(self, method_name): method = getattr(self, method_name) self.mcp.add_tool(method) logger.debug(f"Registered tool: {method_name}") else: logger.warning(f"Method {method_name} not found for tool registration")