pdf-chapter-splitter
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_pdf_infoA | Get PDF metadata (title, author, page count, file size) |
| get_tocB | Extract table of contents (bookmarks/outline) from a PDF. Returns hierarchical chapter structure with page numbers. |
| list_chaptersA | List chapters/sections detected from the PDF. Uses TOC if available, otherwise splits by pages. Returns chapter index, title, page range, and estimated line count. |
| read_chapterA | Read the text content of a specific chapter by its index (from list_chapters). Automatically truncates to stay within Claude Code's context limits. |
| read_pagesA | Read text content from a specific page range. Use this for fine-grained control or when chapters are too large. |
| detect_headingsA | Detect heading candidates by analyzing font sizes. Useful for PDFs without TOC/bookmarks to understand document structure before reading. |
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
Most tools are clearly distinct: metadata, TOC extraction, chapter listing, and raw page reading each have a clear purpose. get_toc, list_chapters, and detect_headings all relate to structure, but their descriptions clarify raw bookmarks vs. detected chapters vs. heading candidates.
All tool names follow a consistent verb_noun pattern: get_pdf_info, get_toc, list_chapters, read_chapter, read_pages, detect_headings. The verbs are varied but predictable based on the action, making the set easy to navigate.
Six tools is a well-scoped size for this server. Each tool covers a distinct aspect of PDF chapter analysis without unnecessary redundancy or overwhelming breadth.
The toolset thoroughly covers analyzing a PDF and reading chapter content, but the server is named 'pdf-chapter-splitter' and provides no actual split, extract, or export operation. An agent could identify chapters and read them, but could not produce split chapter files as the server's name implies.