SCMCP

Instructions

Implementation Reference

• src/scmcp/tool/pp.py:120-137 (handler)

  Generic handler that executes the scanpy pp function (sc.pp.log1p for 'log1p') on the active AnnData object with validated arguments and inplace=True, also logs the operation.

  def run_pp_func(ads, func, arguments):
      adata = ads.adata_dic[ads.active]
      if func not in pp_func:
          raise ValueError(f"不支持的函数: {func}")
      
      run_func = pp_func[func]
      parameters = inspect.signature(run_func).parameters
      arguments["inplace"] = True
      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 KeyError as e:
          raise KeyError(f"Can not foud {e} column in adata.obs or adata.var")
      except Exception as e:
         raise e
      return res

• src/scmcp/schema/pp.py:127-161 (schema)

  Pydantic model for input validation of log1p tool parameters: base, chunked, chunk_size, layer, obsm.

  class Log1PModel(JSONParsingModel):
      """Input schema for the log1p preprocessing tool."""
      
      base: Optional[Union[int, float]] = Field(
          default=None,
          description="Base of the logarithm. Natural logarithm is used by default."
      )
      
      chunked: Optional[bool] = Field(
          default=None,
          description="Process the data matrix in chunks, which will save memory."
      )
      
      chunk_size: Optional[int] = Field(
          default=None,
          description="Number of observations in the chunks to process the data in."
      )
      
      layer: Optional[str] = Field(
          default=None,
          description="Entry of layers to transform."
      )
      
      obsm: Optional[str] = Field(
          default=None,
          description="Entry of obsm to transform."
      )
      
      @field_validator('chunk_size')
      def validate_chunk_size(cls, v: Optional[int]) -> Optional[int]:
          """Validate chunk_size is positive integer"""
          if v is not None and v <= 0:
              raise ValueError("chunk_size must be a positive integer")
          return v

• src/scmcp/tool/pp.py:33-37 (registration)

  Registers the 'log1p' tool using mcp.types.Tool with name, description, and reference to Log1PModel schema.

  log1p = types.Tool(
      name="log1p",
      description="Logarithmize the data matrix (X = log(X + 1))",
      inputSchema=Log1PModel.model_json_schema(),
  )

• src/scmcp/tool/pp.py:88-101 (helper)

  Maps 'log1p' tool name to the underlying sc.pp.log1p function used by the handler.

  pp_func = {
      "filter_genes": sc.pp.filter_genes,
      "filter_cells": sc.pp.filter_cells,
      "calculate_qc_metrics": partial(sc.pp.calculate_qc_metrics, inplace=True),
      "log1p": sc.pp.log1p,
      "normalize_total": sc.pp.normalize_total,
      "pca": sc.pp.pca,
      "highly_variable_genes": sc.pp.highly_variable_genes,
      "regress_out": sc.pp.regress_out,
      "scale": sc.pp.scale,
      "combat": sc.pp.combat,
      "scrublet": sc.pp.scrublet,
      "neighbors": sc.pp.neighbors,
  }

• src/scmcp/tool/pp.py:104-117 (registration)

  Adds the log1p Tool object to the pp_tools dictionary, which is used for listing tools in the MCP server.

  pp_tools = {
      "filter_genes": filter_genes,
      "filter_cells": filter_cells,
      "calculate_qc_metrics": calculate_qc_metrics,
      "log1p": log1p,
      "normalize_total": normalize_total,
      "pca": pca,
      "highly_variable_genes": highly_variable_genes,
      "regress_out": regress_out,
      "scale": scale,
      "combat": combat,
      "scrublet": scrublet,
      "neighbors": neighbors,
  }