SCMCP

Instructions

Implementation Reference

• src/scmcp/schema/tl.py:823-864 (schema)

  Pydantic model defining the input schema and validation for the score_genes tool.
  class ScoreGenesModel(JSONParsingModel): """Input schema for the score_genes tool that calculates gene scores based on average expression.""" ctrl_size: int = Field( default=50, description="Number of reference genes to be sampled from each bin.", gt=0 ) 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: str = Field( default='score', description="Name of the field to be added in .obs." ) 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('ctrl_size', 'n_bins') def validate_positive_integers(cls, v: int) -> int: """Validate positive integers""" if v <= 0: raise ValueError("must be a positive integer") return v
• src/scmcp/tool/tl.py:110-115 (registration)

  Registers the score_genes tool as an MCP Tool instance with name, description, and input schema reference.
  # Add score_genes tool score_genes_tool = types.Tool( name="score_genes", description="Score a set of genes based on their average expression", inputSchema=ScoreGenesModel.model_json_schema(), )
• src/scmcp/tool/tl.py:125-142 (helper)

  Maps tool name 'score_genes' to the underlying scanpy function sc.tl.score_genes 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:164-177 (handler)

  Handler function that executes the score_genes tool logic by calling the mapped scanpy function with input arguments and logging the operation.
  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
• src/scmcp/tool/tl.py:145-162 (registration)

  Adds the score_genes tool to the tl_tools dictionary for module-level tool collection and export.
  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, }