reknihy-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REKNIHY_BASE_URL | No | API origin; defaults to https://reknihy.cz | https://reknihy.cz |
| REKNIHY_TIMEOUT_MS | No | Request timeout in milliseconds; defaults to 15000 | 15000 |
| REKNIHY_CACHE_TTL_MS | No | Cache lifetime in milliseconds; defaults to 60000 and cannot exceed 300000 | 60000 |
| REKNIHY_MAX_CONCURRENT | No | Maximum concurrent upstream requests; defaults to 2 and cannot exceed 4 | 2 |
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 |
|---|---|
| search_booksA | Search the public Reknihy.cz catalog. Use author for exact author searches. Returns price, availability, ISBN, image, categories, and product URL. |
| get_bookA | Get book details by the numeric product ID returned from search_books. |
| find_book_by_isbnA | Find an exact ISBN-10 or ISBN-13 match in the public Reknihy.cz catalog. |
| list_categoriesA | List public catalog categories. A category slug or ID can be passed to search_books. |
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 4 tools
Each tool targets a distinct purpose: broad search, detail lookup by ID, exact ISBN lookup, and category listing. search_books and find_book_by_isbn could be confused since both return books, but the descriptions clearly separate keyword/author search from exact ISBN matching.
All tools follow a consistent verb_noun pattern: search_books, get_book, find_book_by_isbn, list_categories. The naming is predictable and clearly communicates each action.
Four tools is well-scoped for a read-only catalog search server. Each tool has a clear role, and none feel redundant or unnecessary.
The surface covers the full catalog search workflow: discover categories, search books, look up details by ID, and find exact matches by ISBN. For a public catalog querying server, there are no meaningful gaps.