Best for
- Node.js services that want to own backend workbook calculations without a UI.
- AI agents that need tools to interact with spreadsheets with formula readback.
Bilig WorkPaper provides a unique way for agents and Node services to handle formula-driven workbooks without a spreadsheet UI. It offers verified read/write/readback and JSON persistence, making it useful for workflows like pricing and approvals. However, it does not claim full Excel compatibility, and accuracy depends on its own formula engine.
Strongest · Documentation 16/20 Weakest · Reliability 10/20
Static review · not runListed 2026-09-08
Read the FMRS scoring method →Runtime:Node.js 22+ · Hosted (no local runtime)
Run the local stdio server: npm exec --package @bilig/workpaper@latest -- bilig-workpaper-mcp. For a hosted HTTP endpoint, use https://bilig.proompteng.ai/mcp. Before use, verify the npm package's SLSA provenance: npm view @bilig/workpaper version dist.attestations --json.
Run npm exec --yes --package @bilig/workpaper@latest -- bilig-evaluate --door agent-mcp --; when it returns verified: true and the client's tool list shows list_sheets, read_range, set_cell_contents, and the other WorkPaper tools, the MCP server connection is confirmed.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
The Bilig WorkPaper server is an MCP server that lets AI agents and Node.js services programmatically work with spreadsheet formulas. It enables editing cells, recalculating formulas, reading computed outputs, and persisting workbook state as JSON. This server is designed for 'workbook-shaped' business logic, such as pricing models, quote approval, payout checks, and import validation. It runs headless without Excel, and provides tools like read_range and set_cell_contents_and_readback for cell operations with before/after computed readback. It can be run as a local stdio process (recommended for persistence) or accessed via a hosted HTTP endpoint. Note: it does not claim Excel parity and has known compatibility limitations. The source repository documents these for further review.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision 49db26b4bcaa Data synced 2026-10-19 Read the FMRS scoring method