Knihobot MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNIHOBOT_BASE_URL | No | API origin; defaults to https://knihobot.cz | https://knihobot.cz |
| KNIHOBOT_TIMEOUT_MS | No | Request timeout in milliseconds; defaults to 10000 | 10000 |
| KNIHOBOT_CACHE_TTL_MS | No | Cache lifetime in milliseconds; defaults to 60000 and cannot exceed 300000 | 60000 |
| KNIHOBOT_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 Knihobot catalog. Returns sale-ready title groups with the highlighted physical copy, price, availability and IDs needed by the detail tools. |
| suggest_booksB | Return fast public suggestions for books, authors, publishers, categories, labels and series. |
| get_book_detailA | Get metadata and live sale information for one physical copy. Use titleId and bookId returned by search_books or suggest_books. |
| list_available_copiesA | List physical copies currently offered for one edition. Use editionId returned by get_book_detail or search_books. |
| get_recommendationsA | Return books recommended by Knihobot for a specific edition. |
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 5 tools
Each tool targets a distinct operation: catalog search, fast suggestions, physical-copy detail, edition copy listing, and recommendations. The descriptions clearly explain when to use each tool and which IDs are required, so an agent should be able to disambiguate without confusion.
All tool names follow a consistent verb_noun snake_case pattern: search_books, suggest_books, get_book_detail, list_available_copies, get_recommendations. The verbs and nouns are predictable and convey the operation and resource clearly.
Five tools is a well-scoped size for a catalog-focused MCP server. Each tool covers a distinct browsing or lookup need without redundancy or unnecessary surface area.
The tool set covers the core read-only catalog workflow: discovering books through search or suggestions, viewing physical-copy details, listing available copies, and getting recommendations. Purchase, account, or inventory-management features are absent, but those appear outside the intended public catalog scope.