Biomart MCP

Instructions

Lists all available attributes for a given dataset with some filtering.

This function returns a filtered list of all attributes available for the specified
dataset. Some less commonly used attributes (homologs, microarray probes) are
filtered out to reduce the response size.

CAUTION: This function can return a large number of attributes and may be unstable
for certain datasets. Consider using list_common_attributes first.

Args:
    mart (str): The mart identifier (e.g., "ENSEMBL_MART_ENSEMBL")
    dataset (str): The dataset identifier (e.g., "hsapiens_gene_ensembl")

Returns:
    str: CSV-formatted table of all filtered attributes.

Example:
    list_all_attributes("ENSEMBL_MART_ENSEMBL", "hsapiens_gene_ensembl")

Implementation Reference

• biomart-mcp.py:149-177 (handler)

  The handler function for the 'list_all_attributes' MCP tool. Decorated with @mcp.tool() for automatic registration and schema inference from type hints and docstring. Lists filtered attributes for a Biomart dataset and returns as CSV.

  @mcp.tool()
  def list_all_attributes(mart: str, dataset: str):
      """
      Lists all available attributes for a given dataset with some filtering.
  
      This function returns a filtered list of all attributes available for the specified
      dataset. Some less commonly used attributes (homologs, microarray probes) are
      filtered out to reduce the response size.
  
      CAUTION: This function can return a large number of attributes and may be unstable
      for certain datasets. Consider using list_common_attributes first.
  
      Args:
          mart (str): The mart identifier (e.g., "ENSEMBL_MART_ENSEMBL")
          dataset (str): The dataset identifier (e.g., "hsapiens_gene_ensembl")
  
      Returns:
          str: CSV-formatted table of all filtered attributes.
  
      Example:
          list_all_attributes("ENSEMBL_MART_ENSEMBL", "hsapiens_gene_ensembl")
      """
      server = pybiomart.Server(host=DEFAULT_HOST)
      df = server[mart][dataset].list_attributes()
      df = df[~df["name"].str.contains("_homolog_", na=False)]
      df = df[~df["name"].str.contains("dbass", na=False)]
      df = df[~df["name"].str.contains("affy_", na=False)]
      df = df[~df["name"].str.contains("agilent_", na=False)]
      return df.to_csv(index=False).replace("\r", "")