SCMCP

Instructions

Implementation Reference

• src/scmcp/schema/tl.py:866-912 (schema)

  Pydantic model defining input schema for the score_genes_cell_cycle tool, including required S-phase and G2M-phase gene lists and optional parameters.
  class ScoreGenesCellCycleModel(JSONParsingModel): """Input schema for the score_genes_cell_cycle tool that scores cell cycle genes.""" s_genes: List[str] = Field( ..., # Required field description="List of genes associated with S phase." ) g2m_genes: List[str] = Field( ..., # Required field description="List of genes associated with G2M phase." ) gene_pool: Optional[List[str]] = Field( default=None, description="Genes for sampling the reference set. Default is all genes." ) n_bins: int = Field( default=25, description="Number of expression level bins for sampling.", gt=0 ) score_name: Optional[str] = Field( default=None, description="Name of the field to be added in .obs. If None, the scores are added as 'S_score' and 'G2M_score'." ) random_state: int = Field( default=0, description="The random seed for sampling." ) use_raw: Optional[bool] = Field( default=None, description="Whether to use raw attribute of adata. Defaults to True if .raw is present." ) @field_validator('s_genes', 'g2m_genes') def validate_gene_lists(cls, v: List[str]) -> List[str]: """Validate gene lists are not empty""" if len(v) == 0: raise ValueError("Gene list cannot be empty") return v @field_validator('n_bins') def validate_positive_integers(cls, v: int) -> int: """Validate positive integers""" if v <= 0: raise ValueError("n_bins must be a positive integer") return v
• src/scmcp/tool/tl.py:117-122 (registration)

  Registers the MCP tool 'score_genes_cell_cycle' with name, description, and input schema from ScoreGenesCellCycleModel.
  # Add score_genes_cell_cycle tool score_genes_cell_cycle_tool = types.Tool( name="score_genes_cell_cycle", description="Score cell cycle genes and assign cell cycle phases", inputSchema=ScoreGenesCellCycleModel.model_json_schema(), )
• src/scmcp/tool/tl.py:125-142 (handler)

  Maps the tool name 'score_genes_cell_cycle' to scanpy's sc.tl.score_genes_cell_cycle function for execution.
  tl_func = { "tsne": sc.tl.tsne, "umap": sc.tl.umap, "draw_graph": sc.tl.draw_graph, "diffmap": sc.tl.diffmap, "embedding_density": sc.tl.embedding_density, "leiden": sc.tl.leiden, "louvain": sc.tl.louvain, "dendrogram": sc.tl.dendrogram, "dpt": sc.tl.dpt, "paga": sc.tl.paga, "ingest": sc.tl.ingest, "rank_genes_groups": sc.tl.rank_genes_groups, "filter_rank_genes_groups": sc.tl.filter_rank_genes_groups, "marker_gene_overlap": sc.tl.marker_gene_overlap, "score_genes": sc.tl.score_genes, "score_genes_cell_cycle": sc.tl.score_genes_cell_cycle, }
• src/scmcp/tool/tl.py:145-162 (registration)

  Adds the score_genes_cell_cycle_tool to the tl_tools dictionary, likely used for MCP tool listing.
  tl_tools = { "tsne": tsne_tool, "umap": umap_tool, "draw_graph": draw_graph_tool, "diffmap": diffmap_tool, "embedding_density": embedding_density_tool, "leiden": leiden_tool, "louvain": louvain_tool, "dendrogram": dendrogram_tool, "dpt": dpt_tool, "paga": paga_tool, "ingest": ingest_tool, "rank_genes_groups": rank_genes_groups_tool, "filter_rank_genes_groups": filter_rank_genes_groups_tool, "marker_gene_overlap": marker_gene_overlap_tool, "score_genes": score_genes_tool, "score_genes_cell_cycle": score_genes_cell_cycle_tool, }
• src/scmcp/tool/tl.py:164-177 (handler)

  Executes tl tools: retrieves adata, maps func name to scanpy function via tl_func, inspects parameters, calls with provided arguments, logs operation, handles errors.
  def run_tl_func(ads, func, arguments): adata = ads.adata_dic[ads.active] if func not in tl_func: raise ValueError(f"Unsupported function: {func}") run_func = tl_func[func] parameters = inspect.signature(run_func).parameters kwargs = {k: arguments.get(k) for k in parameters if k in arguments} try: res = run_func(adata, **kwargs) add_op_log(adata, run_func, kwargs) except Exception as e: logger.error(f"Error running function {func}: {e}") raise return