calibre-mcp

Overview Schema Source Related Servers Discussions Admin

Semantic search

calibre_semantic_search

Read-only

Meaning-based search over the local index. scope=library ranks books; scope=book (needs bookId) ranks passages within one book.

Instructions

Meaning-based search over the local index. scope=library ranks books; scope=book (needs bookId) ranks passages within one book. target=figures searches figure captions instead of text — use when the user asks for a diagram/chart/schema; hits point at calibre_get_figures for the pixels. mode=hybrid (default) fuses semantic + keyword matches; mode=vector is semantic-only; mode=keyword is exact keyword/FTS (no model at query time). All modes need an index built by calibre_build_index. filter accepts a bundle name to scope library searches (list bundles via calibre_manage_bundles). Model inference is serialized: prefer one call at a time — parallel calls queue, and past a few the extras skip the rerank.

Input Schema

Name	Required	Default
`mode`	No	hybrid
`topK`	No
`query`	Yes
`scope`	No	library
`bookId`	No
`filter`	No
`target`	No	text
`library`	No
`include_excluded`	No

Output Schema

Name	Required	Description	Default
`mode`	No
`note`	No
`count`	No
`scope`	No
`bookId`	No
`filter`	No
`target`	No
`bookIds`	No
`figures`	No
`results`	No
`maxScore`	No
`passages`	No
`reranked`	No
`maxRerank`	No
`indexVersion`	No
`lowConfidence`	No
`semanticReason`	No
`exclusionsApplied`	No
`semanticAvailable`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.7.6Oct 22, 2026
- addedOutput schema / properties / indexVersion
```
Added value: +{
+  "type": "number"
+}
```

Changed4 schema fields changedv0.7.3Aug 18, 2026

addedInput schema / properties / filter

Added value: +{
+  "maxLength": 256,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / include_excluded
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / exclusionsApplied

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / filter
```
Added value: +{
+  "type": "string"
+}
```

First observedv0.7.2Jul 29, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint/openWorldHint; the description adds genuinely new behavioral context: all modes require a pre-built index, model inference is serialized with parallel calls queuing and extras skipping the rerank past a few. This concurrency/throughput disclosure is exactly what annotations cannot convey and directly shapes how an agent should batch calls.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then scope, target, mode, prerequisites, and concurrency in compact sentences with no filler. It is dense to the point of being a run-on in places, but each clause carries operational information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return format is covered elsewhere, and the description supplies the prerequisites, mode semantics, and concurrency caveats an agent needs to call it correctly. The remaining gap is the undocumented topK/library/include_excluded parameters, which affect result shaping and library selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, and it does for the high-impact ones: scope, bookId ("needs bookId"), target, mode, filter (bundle name), and query implicitly. It leaves topK, library, and include_excluded entirely undocumented, so three of nine parameters remain opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("meaning-based search over the local index") and immediately differentiates its two scopes (library vs book) and two targets (text vs figures). An agent can distinguish it from calibre_search and calibre_get_content without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes usage: target=figures "use when the user asks for a diagram/chart/schema", with hits pointing at calibre_get_figures for the pixels; mode selection is spelled out per case (hybrid default, vector semantic-only, keyword FTS). It also names the prerequisite (index built by calibre_build_index) and the sibling for listing filters (calibre_manage_bundles).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server