pl_pca_variance_ratio

Instructions

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pl_pca_variance_ratio"
  }
}

Implementation Reference

• src/scmcp/tool/pl.py:179-216 (handler)

  Generic handler function that executes the tool logic for pl_pca_variance_ratio by calling sc.pl.pca_variance_ratio with validated arguments, saves the figure, and logs the operation.

  def run_pl_func(ads, func, arguments):
      """
      Execute a Scanpy plotting function with the given arguments.
      
      Parameters
      ----------
      adata : AnnData
          Annotated data matrix.
      func : str
          Name of the plotting function to execute.
      arguments : dict
          Arguments to pass to the plotting function.
          
      Returns
      -------
      The result of the plotting function.
      """
      adata = ads.adata_dic[ads.active]
      if func not in pl_func:
          raise ValueError(f"Unsupported function: {func}")
  
      run_func = pl_func[func]
      parameters = inspect.signature(run_func).parameters
      kwargs = {k: arguments.get(k) for k in parameters if k in arguments}    
  
      if "title" not in parameters:
          kwargs.pop("title", False)    
      kwargs.pop("return_fig", True)
      kwargs["show"] = False
      kwargs["save"] = ".png"
      try:
          fig = run_func(adata, **kwargs)
          fig_path = set_fig_path(func, **kwargs)
          add_op_log(adata, run_func, kwargs)
          return fig_path 
      except Exception as e:
          raise e
      return fig_path

• src/scmcp/schema/pl.py:816-836 (schema)

  Pydantic model defining the input schema (parameters like n_pcs, log) for the pl_pca_variance_ratio tool.

  class PCAVarianceRatioModel(BaseVisualizationModel):
      """Input schema for the pca_variance_ratio plotting tool."""
      
      n_pcs: int = Field(
          default=30,
          description="Number of PCs to show.",
          gt=0
      )
      
      log: bool = Field(
          default=False,
          description="Plot on logarithmic scale."
      )
      
      @field_validator('n_pcs')
      def validate_n_pcs(cls, v: int) -> int:
          """Validate n_pcs is positive"""
          if v <= 0:
              raise ValueError("n_pcs must be a positive integer")
          return v

• src/scmcp/tool/pl.py:113-117 (registration)

  Creates the MCP types.Tool instance for pl_pca_variance_ratio, specifying name, description, and input schema.

  pl_pca_variance_ratio = types.Tool(
      name="pl_pca_variance_ratio",
      description="Plot the PCA variance ratio to visualize explained variance.",
      inputSchema=PCAVarianceRatioModel.model_json_schema(),
  )

• src/scmcp/tool/pl.py:121-138 (registration)

  Maps the tool name 'pl_pca_variance_ratio' to the underlying scanpy function sc.pl.pca_variance_ratio for execution.

  pl_func = {
      "pl_pca": sc.pl.pca,
      "pl_embedding": sc.pl.embedding,  # Add the new embedding function
      "diffmap": sc.pl.diffmap,
      "pl_violin": sc.pl.violin,
      "pl_stacked_violin": sc.pl.stacked_violin,
      "pl_heatmap": sc.pl.heatmap,
      "pl_dotplot": sc.pl.dotplot,
      "pl_matrixplot": sc.pl.matrixplot,
      "pl_tracksplot": sc.pl.tracksplot,
      "pl_scatter": sc.pl.scatter,
      "embedding_density": sc.pl.embedding_density,
      "rank_genes_groups": sc.pl.rank_genes_groups,
      "pl_rank_genes_groups_dotplot": sc.pl.rank_genes_groups_dotplot,  # Add function mapping
      "pl_clustermap": sc.pl.clustermap,
      "pl_highly_variable_genes": sc.pl.highly_variable_genes,
      "pl_pca_variance_ratio": sc.pl.pca_variance_ratio,
  }

• src/scmcp/server.py:71-72 (registration)

  In the MCP call_tool handler, checks if the tool name is in pl_tools and dispatches to run_pl_func.

  elif name in pl_tools.keys():
      res = run_pl_func(ads, name, arguments)