load_csv_from_content
Load CSV data directly from string content to process and manipulate tabular information within the CSV Editor MCP server.
Instructions
Load CSV data from string content.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| delimiter | No | , | |
| session_id | No | ||
| has_header | No |
Implementation Reference
- Core handler function that implements the tool logic: parses CSV content from string using pandas.read_csv with StringIO, loads DataFrame into a session, and returns detailed OperationResult.async def load_csv_from_content( content: str, delimiter: str = ",", session_id: Optional[str] = None, has_header: bool = True, ctx: Context = None ) -> Dict[str, Any]: """Load CSV data from a string content. Args: content: CSV content as string delimiter: Column delimiter session_id: Optional existing session ID has_header: Whether first row is header ctx: FastMCP context Returns: Operation result with session ID and data info """ try: if ctx: await ctx.info("Loading CSV from content string") # Parse CSV from string from io import StringIO df = pd.read_csv( StringIO(content), delimiter=delimiter, header=0 if has_header else None ) # Get or create session session_manager = get_session_manager() session = session_manager.get_or_create_session(session_id) session.load_data(df, None) if ctx: await ctx.info(f"Loaded {len(df)} rows and {len(df.columns)} columns") return OperationResult( success=True, message=f"Successfully loaded CSV from content", session_id=session.session_id, rows_affected=len(df), columns_affected=df.columns.tolist(), data={ "shape": df.shape, "preview": df.head(5).to_dict('records') } ).model_dump() except Exception as e: if ctx: await ctx.error(f"Failed to parse CSV content: {str(e)}") return OperationResult( success=False, message="Failed to parse CSV content", error=str(e) ).model_dump()
- src/csv_editor/server.py:133-142 (registration)MCP tool registration using @mcp.tool decorator. Thin wrapper that imports and delegates to the core implementation in io_operations.py.@mcp.tool async def load_csv_from_content( content: str, delimiter: str = ",", session_id: Optional[str] = None, has_header: bool = True, ctx: Context = None ) -> Dict[str, Any]: """Load CSV data from string content.""" return await _load_csv_from_content(content, delimiter, session_id, has_header, ctx)
- src/csv_editor/server.py:98-106 (registration)Import of the core load_csv_from_content function (aliased as _load_csv_from_content) used by the registered tool wrapper.from .tools.io_operations import ( load_csv as _load_csv, load_csv_from_url as _load_csv_from_url, load_csv_from_content as _load_csv_from_content, export_csv as _export_csv, get_session_info as _get_session_info, list_sessions as _list_sessions, close_session as _close_session )