Convert between file formats: PDF pages to JPG/PNG, images to one PDF, XLSX/CSV to CSV/JSON, HWP/HWPX to PDF/HWP/HWPX. Each output is reopened and checked, and missed content is reported.
Generate a Meep FDTD simulation script from a natural-language problem description. Returns runnable Python and an explanation; pass a previous error trace to patch failed runs.
Extract readable text from images, screenshots, photos, and scanned PDFs via OCR. Returns reading-order text with confidence and optional bounding boxes for receipts, invoices, and forms.
Export a session as a runnable Python script that regenerates the model, drawings, and simulations, with checks and provenance for every computed result.
Capture the current page as a PNG and return its file path so agents can visually inspect layout, images, and charts that text extraction cannot convey.
A local MCP server for analyzing CSV files from your filesystem, particularly suited for chatbot conversation logs. Allows listing, reading, filtering, merging, and statistical analysis of CSV data via natural language.
Cut character PNG into named polygon parts for cutout rigging. Outputs each part as PNG, a base image with parts erased, and bounding boxes for placement.
Convert PDF and scanned images to structured CSV data, preserving layout, columns, rows, and tables. Extracts tabular content from documents for easy analysis.
Create a TouchDesigner DAT node preloaded with your Python code, choosing between text, execute, or script types. Stores code as a node for later execution.
Fetch attachment content from a Plane work item to read or analyze images and text files. Supports PNG, JPEG, GIF, WEBP and TXT, MD, CSV, HTML, XML, YAML, JSON, returning vision images or strings.
Retrieve the content of a work item attachment for analysis, returning images as vision-readable objects and text files as strings. Supports PNG, JPEG, GIF, WEBP, and text formats up to specified size limits.