TruePath PDF MCP Server
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 |
|---|---|
| get_infoA | Return page count, first-page size, encryption status, and embedded metadata (title, author, dates, producer, etc.) for a local PDF. |
| extract_textA | Extract plain text from a local PDF. Optionally restrict to a page range like "1-5" or "1,3,5-7". Output is split by page with === Page N === markers. |
| searchA | Find a substring across the whole PDF. Returns each hit's page, offset within the page, and a snippet of surrounding text. Use for grep-style discovery before extracting full text. |
| splitA | Split a PDF into multiple PDFs by page ranges. Each range becomes one output file written into outputDir. |
| mergeA | Combine two or more PDFs into one, preserving page order. Outputs to a caller-specified path. |
| pagesA | One-pass page editor. Delete pages, rotate specific pages by 90°/180°/270°, and reorder the result — in any combination. Page numbers in |
| to_imagesA | Rasterize PDF pages as PNG or JPG at a chosen DPI. Useful for previews, OCR pipelines, or feeding pages back to a vision model. |
| extract_imagesA | Pull embedded images out of a PDF and write each as a PNG. Unsupported pixel layouts (e.g. CMYK, palettized) are skipped and reported. |
| open_in_truepathA | Hand a local PDF to the TruePath PDF Mac app via its truepath:// URL scheme so the user can finish work in a GUI (annotate, sign, fill forms, redact). The bridge is fire-and-forget — the app handles opening from there. Requires the app installed (https://joytruepath.com/truepath-pdf). |
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
Most tools target clearly distinct operations: metadata, merge, text extraction, search, split, page editing, rasterization, embedded-image extraction, and GUI handoff. The only potential confusion is between to_images and extract_images, but their descriptions make the raster-vs-embedded distinction clear.
Naming is readable and lowercase but stylistically mixed: some tools use verb_noun (get_info, extract_text, extract_images), some are bare verbs (merge, search, split), and others are unconventional (pages, to_images, open_in_truepath). This is not chaotic, but it lacks a strong consistent pattern.
Nine tools is a well-scoped set for a PDF-focused server. Each tool covers a distinct PDF workflow without feeling padded, and the count fits comfortably in the ideal range.
The server covers core PDF workflows well: inspection, text extraction, searching, splitting, merging, page-level editing, rendering to images, extracting embedded images, and handoff to a GUI. Minor gaps exist around metadata editing, encryption, and annotation, but open_in_truepath provides a reasonable escape hatch for those advanced operations.