spreadsheet-read-mcp
by PSU3D0
Overview
An LLM-friendly API server for analyzing and editing spreadsheet files, enabling 'discover → profile → extract' workflows, 'what-if' scenarios, and VBA inspection without dumping entire files into LLM context.
Installation
docker run -v /path/to/workbooks:/data -p 8079:8079 ghcr.io/psu3d0/spreadsheet-mcp:fullEnvironment Variables
- SPREADSHEET_MCP_WORKSPACE
- SPREADSHEET_MCP_CACHE_CAPACITY
- SPREADSHEET_MCP_EXTENSIONS
- SPREADSHEET_MCP_WORKBOOK
- SPREADSHEET_MCP_ENABLED_TOOLS
- SPREADSHEET_MCP_TRANSPORT
- SPREADSHEET_MCP_HTTP_BIND
- SPREADSHEET_MCP_RECALC_ENABLED
- SPREADSHEET_MCP_VBA_ENABLED
- SPREADSHEET_MCP_MAX_CONCURRENT_RECALCS
- SPREADSHEET_MCP_TOOL_TIMEOUT_MS
- SPREADSHEET_MCP_MAX_RESPONSE_BYTES
- SPREADSHEET_MCP_ALLOW_OVERWRITE
Security Notes
External execution of LibreOffice (`soffice`) for recalculation and screenshots introduces a significant attack surface. While the server implements strong path validation (`workspace_root`) to prevent path traversal and resource limits (file size, cache, concurrent processes, response size) to mitigate DoS, the security of LibreOffice's macro execution environment and the specific custom macros (source not provided) are critical points of trust. The project strongly recommends running write/recalc features within a Docker container for isolation. Parsing complex Excel files via `umya_spreadsheet` also presents potential vulnerabilities. The server allows explicit control over overwriting original files via the `--allow-overwrite` flag.
Similar Servers
excel-mcp-server
This server allows AI agents to manipulate Excel files (create, read, update, format, chart, pivot, validate) without requiring Microsoft Excel to be installed.
code-assistant
Standardizes communication between code editors and AI coding agents, enabling autonomous code analysis and modification via command-line, GUI, or server modes.
spreadsheet-mcp
Analyze and edit spreadsheet files programmatically, designed for token-efficient interaction by LLM agents, focusing on structured data access, modification, formula analysis, and optional VBA inspection.
academia_mcp
An MCP server providing tools for searching, fetching, analyzing, and reporting on scientific papers and datasets, often powered by LLMs.