book-recommendations
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recommendB | Book recommendations by topic, mood, or 'books like X' — millions of works, free-read flags included |
| blind_dateC | Serendipity spin: a random shelf at random depth — present the first sentence first, then the reveal |
| free_classicsC | Public-domain classics from Project Gutenberg, readable in full right now |
| skills_listA | List available skills (guidance playbooks) for using this server well — read one with skill_read |
| skill_readA | Fetch the full content of one skill by name (from skills_list) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| what-should-i-read-next | Book recommendations from a mood, a topic, or nothing at all (blind date). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| interpreting-errors | Error shapes — no matches, transient upstream failures, and the Gutenberg fallback path. |
| presenting-recommendations | How to present a card — the blind-date two-beat reveal and honesty rules. |
TDQS
Scored across 5 tools
Each tool serves a clearly distinct purpose: recommend provides targeted recommendations, blind_date offers random serendipity, free_classics surfaces public-domain works, and skills_list/skill_read manage usage guidance. No overlap or ambiguity exists between the tools.
Tool names follow no consistent pattern: 'recommend' is a bare verb, 'blind_date' and 'free_classics' are noun phrases, while 'skills_list' is a noun-noun compound and 'skill_read' reverses the typical verb-object order. This mixed convention could cause confusion about expected behavior.
With just 5 tools, the server is tightly scoped for its domain. Each tool adds distinct value without redundancy, and the count is well within the ideal range for a focused MCP server.
The core recommendation workflows are covered: tailored recommendations, serendipitous discovery, and access to classics. However, missing operations like fetching book details or saving favorites create minor gaps, though agents can likely work around them for most use cases.