download-books-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BOOK_PROVIDER_2_EMAIL | No | Email for Z-Library / Zeta Library authentication (optional). | |
| DOWNLOAD_BOOKS_PROVIDER | No | Provider to use for book search: 'all', 'provider_1', or 'provider_2'. Default is 'all'. | all |
| BOOK_PROVIDER_2_PASSWORD | No | Password for Z-Library / Zeta Library authentication (optional). | |
| DOWNLOAD_BOOKS_LIBRARY_DIR | No | Directory where downloaded books are stored. | ~/Downloads/books |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_booksA | Search book metadata through configured providers. Returns clean results with an id for download_book. |
| download_bookA | Download a book selected by its id from a previous search_books result. |
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 2 tools
The two tools have clearly distinct purposes: one searches for books and returns metadata with IDs, the other downloads a specific book by ID. There is no overlap or ambiguity between them.
Both tools follow a consistent verb_noun pattern: search_books and download_book. The slight singular/plural difference is natural and does not create inconsistency.
With only 2 tools, the server is on the thin side, but given its narrow purpose of searching and downloading books, this count is appropriate and each tool clearly earns its place.
The server covers the essential workflow for its domain: discover books via search, then download via ID. This forms a complete user journey with no dead ends or obvious missing operations.