stayput-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pdf_infoA | Read a PDF on this machine and report its page count, page sizes, title and whether it was encrypted. Read-only: nothing is written. Use before split_pdf, extract_pdf_pages or rotate_pdf to learn the page count. Fails with a readable error if the file is not a PDF or needs a password. |
| merge_pdfsA | Combine several PDFs on this machine into one, in the order given. The same file may appear more than once. Writes a new PDF and returns its path; the inputs are never modified and an existing file is never overwritten. To combine only some pages, run extract_pdf_pages first. Needs the optional password if an input is encrypted. |
| extract_pdf_pagesA | Write a new PDF containing only the listed pages, in the listed order. Use it to pull out a range, reorder pages ("3,1,2") or drop pages (list the ones to keep). Pages are 1-based; ranges like "1-3, 7" and reversed ranges like "5-1" work. Writes a new PDF and returns its path; the input is not modified and an existing file is never overwritten. To cut a PDF into equal parts use split_pdf instead. |
| split_pdfA | Split a PDF into several files of N pages each (1 = one file per page), written into a folder. Returns the list of files. The input is not modified and existing files are never overwritten. To keep a custom page range as one file use extract_pdf_pages instead. |
| rotate_pdfA | Rotate all pages, or only the listed ones, clockwise by 90, 180 or 270 degrees, and save the rotation permanently in a new PDF. The input is not modified and an existing file is never overwritten; returns the new path. |
| number_pdf_pagesA | Stamp page numbers on a PDF. The template may use {n} for the page number and {total} for the last number, e.g. "Page {n} of {total}". Writes a new PDF and returns its path; the input is not modified and an existing file is never overwritten. Text only, in Helvetica. |
| images_to_pdfA | Put JPG and PNG images into one PDF, one image per page, in the order given. Images are embedded as they are, without re-compression. HEIC and WebP are rejected with an error that says how to convert them. Writes a new PDF and returns its path; an existing file is never overwritten. |
| inspect_image_metadataA | Report the metadata hidden in a JPG, PNG or WebP photo: GPS location, camera make and model, capture time, editing software, and which blocks (EXIF, XMP, IPTC, comments) are present. HEIC files report EXIF only. Read-only: nothing is written. Use before strip_image_metadata to see what would be removed. |
| strip_image_metadataA | Write a copy of a JPG, PNG or WebP photo with EXIF (including GPS location), XMP, IPTC and comments removed. Lossless: the image data is not re-encoded. The original file is left untouched and an existing file is never overwritten; returns the new path and what was removed. HEIC is rejected with an error. Use inspect_image_metadata first to see what is there. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct file operation, and overlapping cases like split_pdf vs. extract_pdf_pages are explicitly differentiated in their descriptions. Read-only and modifying variants (pdf_info, inspect_image_metadata vs. strip_image_metadata) are clearly separated.
Most names follow a consistent snake_case verb_noun pattern (split_pdf, merge_pdfs, rotate_pdf, extract_pdf_pages). Minor deviations like pdf_info (noun-first) and images_to_pdf (noun_to_noun) are still readable and predictable.
9 tools is well within the ideal range for a PDF/image utility server. Each tool covers a unique operation, and none feels redundant or trivial.
The set covers core PDF operations (info, split, merge, extract, rotate, number) and image metadata handling. However, it lacks PDF encryption/decryption, PDF-to-image conversion, or text extraction, leaving minor gaps that agents would need to work around.