Research prototype that connects Quantrix Modeler, a multidimensional spreadsheet for financial modelling, to the Claude AI assistant through the Model Context Protocol (MCP). It has two components: an MCP server in Node.js (version 3.0.0, 12 tools) and an HTTP server embedded in Quantrix as a Groovy scripted action. With them the assistant reads the structure and values of the open model (matrices, categories, items, formulas), explains how a cell is computed through its dependency tree, changes assumptions, builds scenarios and runs scripted actions. Developed by the author between May and November 2025 and used in teaching and research: analysis of financial projections, financial statement analysis of Italian companies, break-even analysis, and semi-automatic review of Quantrix models submitted as course assignments.
Quantrix–Claude MCP bridge (2025): server Model Context Protocol e server HTTP integrato in Quantrix Modeler per l’analisi dei modelli finanziari assistita dall’intelligenza artificiale / Erzegovesi, L.. - ELETTRONICO. - (2025). [10.5281/zenodo.23064178]
Quantrix–Claude MCP bridge (2025): server Model Context Protocol e server HTTP integrato in Quantrix Modeler per l’analisi dei modelli finanziari assistita dall’intelligenza artificiale
Erzegovesi, Luca
2025-01-01
Abstract
Research prototype that connects Quantrix Modeler, a multidimensional spreadsheet for financial modelling, to the Claude AI assistant through the Model Context Protocol (MCP). It has two components: an MCP server in Node.js (version 3.0.0, 12 tools) and an HTTP server embedded in Quantrix as a Groovy scripted action. With them the assistant reads the structure and values of the open model (matrices, categories, items, formulas), explains how a cell is computed through its dependency tree, changes assumptions, builds scenarios and runs scripted actions. Developed by the author between May and November 2025 and used in teaching and research: analysis of financial projections, financial statement analysis of Italian companies, break-even analysis, and semi-automatic review of Quantrix models submitted as course assignments.| File | Dimensione | Formato | |
|---|---|---|---|
|
nota-tecnica-quantrix-mcp-bridge-2025.pdf
accesso aperto
Descrizione: Nota tecnica
Tipologia:
Altro materiale allegato (Other attachments)
Licenza:
Altra licenza (Other type of license)
Dimensione
86.62 kB
Formato
Adobe PDF
|
86.62 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione



