PDF-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": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pdf_read_textC | Extract readable text from a PDF file with optional page range boundaries (1-based index). |
| pdf_get_metadataC | Retrieve technical metadata, total page count, file size, title, and author of a PDF file. |
| pdf_search_batchB | Search across multiple PDF files in a directory matching a pattern (e.g. '.pdf', 'L.pdf') for a keyword or regex. |
| pdf_compare_filesC | Compare two PDF files page by page to detect text differences and page count mismatches. |
| pdf_generate_reportB | Generate a publication-grade, styled PDF document from structured JSON data or an external JSON/Markdown file ('input_file') with cover page, headers/footers, Q&A cards, tables, images, callouts, code blocks, and full Turkish Unicode support. |
| pdf_from_markdownA | Compile a Markdown file (.md) or raw Markdown string directly into a styled, publication-grade PDF report without needing JSON conversion. Supports YAML frontmatter, # sections, ##/### Q&A headers, |
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 6 tools
Each tool targets a distinct operation: metadata, text extraction, batch search, comparison, and two generation paths. The only real overlap is pdf_generate_report vs pdf_from_markdown, both producing styled PDFs, though the descriptions clearly delineate JSON/structured input versus Markdown input.
All tools share a pdf_ prefix and snake_case, with verb-led names (get, read, search, compare, generate). Minor deviations: pdf_search_batch orders noun-before-verb, and pdf_from_markdown uses a preposition rather than an action verb.
Six tools is a tight, well-scoped surface for a PDF utility server, with no redundant entries. Every tool corresponds to a recognizable user task in the PDF lifecycle.
Reading, metadata, search, comparison, and generation from two input formats are covered, but document manipulation operations (split, merge, rotate, page extraction, image extraction, PDF forms) are absent. Agents wanting to modify existing PDFs rather than just read or create them will hit dead ends.