pl_pca

Instructions

Implementation Reference

• src/scmcp/schema/pl.py:751-758 (schema)

  PCAModel defines the input schema (Pydantic model) for the pl_pca tool, inheriting from BaseEmbeddingModel.

  class PCAModel(BaseEmbeddingModel):
      """Input schema for the PCA plotting tool."""
      
      annotate_var_explained: bool = Field(
          default=False,
          description="Annotate the explained variance."
      )

• src/scmcp/tool/pl.py:15-19 (registration)

  Creates and registers the MCP Tool object for pl_pca with name, description, and input schema.

  pl_pca_tool = types.Tool(
      name="pl_pca",
      description="Scatter plot in PCA coordinates. default figure for PCA plot",
      inputSchema=PCAModel.model_json_schema(),
  )

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

  Dictionary mapping tool names like 'pl_pca' to their corresponding Scanpy plotting functions (sc.pl.pca). Used by the handler.

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

  Handler function that executes the pl_pca tool: retrieves adata, prepares kwargs from arguments, calls sc.pl.pca(adata, **kwargs), saves figure, logs operation, returns fig_path.

  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/server.py:60-92 (registration)

  MCP server call_tool handler dispatches to run_pl_func when tool name is in pl_tools (includes pl_pca).

  async def call_tool(
      name: str, arguments
  ):
      try:
          logger.info(f"Running {name} with {arguments}")
          if name in io_tools.keys():            
              res = run_io_func(ads, name, arguments)
          elif name in pp_tools.keys():
              res = run_pp_func(ads, name, arguments)
          elif name in tl_tools.keys():
              res = run_tl_func(ads, name, arguments) 
          elif name in pl_tools.keys():
              res = run_pl_func(ads, name, arguments)
          elif name in util_tools.keys():            
              res = run_util_func(ads, name, arguments)
          elif name in ccc_tools.keys():            
              res = run_ccc_func(ads.adata_dic[ads.active], name, arguments)
          output = str(res) if res is not None else str(ads.adata_dic[ads.active])
          return [
              types.TextContent(
                  type="text",
                  text=str({"output": output})
              )
          ]
      except Exception as error:
          logger.error(f"{name} with {error}")
          return [
              types.TextContent(
                  type="text",
                  text=str({"Error": error})
              )
          ]