get_data

Instructions

Queries Biomart for data using specified attributes and filters.

This function performs the main data retrieval from Biomart, allowing you to
query biological data by specifying which attributes to return and which filters
to apply. Includes automatic retry logic for resilience.

Args:
    mart (str): The mart identifier (e.g., "ENSEMBL_MART_ENSEMBL")
    dataset (str): The dataset identifier (e.g., "hsapiens_gene_ensembl")
    attributes (list[str]): List of attributes to retrieve (e.g., ["ensembl_gene_id", "external_gene_name"])
    filters (dict[str, str]): Dictionary of filters to apply (e.g., {"chromosome_name": "1"})

Returns:
    str: CSV-formatted results of the query.

Example:
    get_data(
        "ENSEMBL_MART_ENSEMBL",
        "hsapiens_gene_ensembl",
        ["ensembl_gene_id", "external_gene_name", "chromosome_name"],
        {"chromosome_name": "X", "biotype": "protein_coding"}
    )
    >>> "ensembl_gene_id,external_gene_name,chromosome_name
         ENSG00000000003,TSPAN6,X
         ENSG00000000005,TNMD,X
         ..."

Implementation Reference

• biomart-mcp.py:207-256 (handler)

  The get_data tool handler: decorated with @mcp.tool() for MCP registration. Executes Biomart query with retry logic using pybiomart, returns CSV data.

  @mcp.tool()
  def get_data(mart: str, dataset: str, attributes: list[str], filters: dict[str, str]):
      """
      Queries Biomart for data using specified attributes and filters.
  
      This function performs the main data retrieval from Biomart, allowing you to
      query biological data by specifying which attributes to return and which filters
      to apply. Includes automatic retry logic for resilience.
  
      Args:
          mart (str): The mart identifier (e.g., "ENSEMBL_MART_ENSEMBL")
          dataset (str): The dataset identifier (e.g., "hsapiens_gene_ensembl")
          attributes (list[str]): List of attributes to retrieve (e.g., ["ensembl_gene_id", "external_gene_name"])
          filters (dict[str, str]): Dictionary of filters to apply (e.g., {"chromosome_name": "1"})
  
      Returns:
          str: CSV-formatted results of the query.
  
      Example:
          get_data(
              "ENSEMBL_MART_ENSEMBL",
              "hsapiens_gene_ensembl",
              ["ensembl_gene_id", "external_gene_name", "chromosome_name"],
              {"chromosome_name": "X", "biotype": "protein_coding"}
          )
          >>> "ensembl_gene_id,external_gene_name,chromosome_name
               ENSG00000000003,TSPAN6,X
               ENSG00000000005,TNMD,X
               ..."
      """
      for attempt in range(MAX_RETRIES):
          try:
              server = get_server()
              return (
                  server[mart][dataset]
                  .query(attributes=attributes, filters=filters)
                  .to_csv(index=False)
                  .replace("\r", "")
              )
          except Exception as e:
              print(
                  f"Error getting data (attempt {attempt+1}/{MAX_RETRIES}): {str(e)}",
                  file=sys.stderr,
              )
              if attempt < MAX_RETRIES - 1:
                  print(f"Retrying in {RETRY_DELAY} seconds...", file=sys.stderr)
                  time.sleep(RETRY_DELAY)
              else:
                  return f"Error: {str(e)}"

• biomart-mcp.py:52-60 (helper)

  Cached helper function to create and retrieve the pybiomart Server connection, used by get_data.

  @lru_cache()
  def get_server():
      """Create and cache a server connection with error handling"""
      try:
          return pybiomart.Server(host=DEFAULT_HOST)
      except Exception as e:
          print(f"Error connecting to Biomart server: {str(e)}", file=sys.stderr)
          raise

• biomart-mcp.py:208-236 (schema)

  Type hints and docstring defining input schema (mart:str, dataset:str, attributes:list[str], filters:dict[str,str]) and output (str: CSV). Note: schema embedded in handler.

  def get_data(mart: str, dataset: str, attributes: list[str], filters: dict[str, str]):
      """
      Queries Biomart for data using specified attributes and filters.
  
      This function performs the main data retrieval from Biomart, allowing you to
      query biological data by specifying which attributes to return and which filters
      to apply. Includes automatic retry logic for resilience.
  
      Args:
          mart (str): The mart identifier (e.g., "ENSEMBL_MART_ENSEMBL")
          dataset (str): The dataset identifier (e.g., "hsapiens_gene_ensembl")
          attributes (list[str]): List of attributes to retrieve (e.g., ["ensembl_gene_id", "external_gene_name"])
          filters (dict[str, str]): Dictionary of filters to apply (e.g., {"chromosome_name": "1"})
  
      Returns:
          str: CSV-formatted results of the query.
  
      Example:
          get_data(
              "ENSEMBL_MART_ENSEMBL",
              "hsapiens_gene_ensembl",
              ["ensembl_gene_id", "external_gene_name", "chromosome_name"],
              {"chromosome_name": "X", "biotype": "protein_coding"}
          )
          >>> "ensembl_gene_id,external_gene_name,chromosome_name
               ENSG00000000003,TSPAN6,X
               ENSG00000000005,TNMD,X
               ..."
      """