Law Scrapper MCP

Instructions

Implementation Reference

• app.py:214-218 (registration)

  Registers the search_legal_acts tool using FastMCP's @app.tool decorator, specifying name, description, and tags.
  @app.tool( name="search_legal_acts", description="Advanced search for Polish legal acts with multiple filters. Use this for finding specific documents by criteria like date, type, keywords, or title. Note: When using multiple keywords, ALL keywords must be present in the act (AND logic).", tags={"search", "acts", "filtering", "legal-research"} )
• app.py:219-231 (schema)

  Defines the input schema and parameters for the search_legal_acts tool using Python's Annotated types with descriptions.
  def get_acts_list( year: Annotated[Union[int, str, None], "Publication year (e.g., 2020, 2023)"] = None, keywords: Annotated[list[str] | None, "List of keywords to search in act content. ALL keywords must be present in the act (AND logic)"] = None, date_from: Annotated[str | None, "Start date for effectiveness period (YYYY-MM-DD)"] = None, date_to: Annotated[str | None, "End date for effectiveness period (YYYY-MM-DD)"] = None, title: Annotated[str | None, "Text fragment to search in act titles"] = None, act_type: Annotated[str | None, "Document type (e.g., 'Rozporządzenie', 'Ustawa')"] = None, pub_date_from: Annotated[str | None, "Start date for publication period (YYYY-MM-DD)"] = None, pub_date_to: Annotated[str | None, "End date for publication period (YYYY-MM-DD)"] = None, in_force: Annotated[Union[bool, str], "Only return currently active acts. Type 'true' for active, 'false' for inactive"] = None, limit: Annotated[Union[int, str, None], "Maximum number of results (default: all matching)"] = None, offset: Annotated[Union[int, str, None], "Skip first N results for pagination"] = None ) -> list:
• app.py:279-325 (handler)

  Implements the core execution logic of the search_legal_acts tool: builds query parameters from inputs, makes HTTP GET request to Sejm API search endpoint, processes response, and returns list of matching legal acts.
  logger.debug(f"get_acts_list called with filters: year={year}, keywords={keywords}, date_from={date_from}, date_to={date_to}, title={title}, act_type={act_type}, pub_date_from={pub_date_from}, pub_date_to={pub_date_to}, in_force={in_force}, limit={limit}, offset={offset}") try: # Build API request parameters from function arguments params = { "publisher": "DU", # Default to Dziennik Ustaw (primary legal gazette) } if year: params["year"] = int(year) if isinstance(year, str) else year if keywords: params["keyword"] = ",".join(keywords) if date_from: params["dateEffectFrom"] = date_from if date_to: params["dateEffectTo"] = date_to if title: params["title"] = title if act_type: params["type"] = act_type if pub_date_from: params["dateFrom"] = pub_date_from if pub_date_to: params["dateTo"] = pub_date_to if in_force is not None: params["inForce"] = bool(in_force) if limit: params["limit"] = int(limit) if isinstance(limit, str) else limit if offset: params["offset"] = int(offset) if isinstance(offset, str) else offset url = "https://api.sejm.gov.pl/eli/acts/search" # Make API request with constructed parameters response = requests.get(url, params=params, headers={"Accept": "application/json"}) response.raise_for_status() data = response.json().get("items", []) if not data: logger.info("get_acts_list returned no results") return [] logger.info(f"get_acts_list returned {len(data)} acts") return data except Exception as e: logger.error(f"Error: {e}") return []