mcp-pdf-utils
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_infoB | Get PDF metadata: page count, title, author, creator, creation date, file size. |
| pdf_extract_textC | Extract text content from a PDF file. Optionally specify page range. |
| pdf_mergeC | Merge multiple PDF files into a single PDF. |
| pdf_splitA | Split a PDF into separate files. Extract specific pages or split into individual page files. |
| pdf_rotateB | Rotate pages of a PDF by 90, 180, or 270 degrees. |
| pdf_add_watermarkC | Add a text watermark to all or specific pages of a PDF. |
| pdf_extract_pagesB | Extract a range of pages from a PDF into a new PDF file. |
| pdf_set_metadataC | Set or update PDF metadata (title, author, subject, keywords, creator). |
| pdf_delete_pagesC | Delete specific pages from a PDF. |
| pdf_reorderB | Reorder pages of a PDF. Provide the desired page order. |
| pdf_createC | Create a new PDF document from plain text content. |
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 11 tools
Each tool has a clearly distinct purpose with no significant overlap. For example, pdf_extract_pages creates a new PDF from a range, while pdf_split divides into separate files, and pdf_delete_pages removes pages without creating new files. The descriptions specify unique actions on PDFs, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with the prefix 'pdf_' (e.g., pdf_add_watermark, pdf_extract_text). This uniform snake_case naming makes the set predictable and easy to understand, enhancing usability for agents.
With 11 tools, the count is well-scoped for PDF manipulation tasks. It covers a comprehensive range of operations without being overwhelming, including creation, editing, extraction, merging, and metadata handling, which aligns perfectly with the server's purpose.
The tool set provides complete coverage for PDF manipulation, including CRUD-like operations (create, modify, delete pages), metadata management, and advanced features like watermarking and rotation. There are no obvious gaps; agents can perform all common PDF tasks without dead ends.