openlibrary-mcp-server

Search Inside Books

openlibrary_search_inside

Read-only

Search the full text of books scanned by the Internet Archive — the "which book contains this passage?" lookup that the metadata tools cannot answer. Quote a phrase for an exact-phrase match; bare terms match anywhere in the text. Each result is an Internet Archive item with the matching passages as snippets, plus a relevance score. The full-text index is far slower than the metadata endpoints, and a search usually takes 10–30 seconds. Use it when the passage is the question, and use openlibrary_search_books to search by title, author, or subject. Results key on Internet Archive items rather than Open Library works: chain the returned ia_identifier to archive.org, or match it against the ia_identifiers on openlibrary_search_books results to reach the catalogue record.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max matching items to return. Each carries its own snippets, so higher values grow the response quickly — prefer 10–20.
`query`	Yes	Text to find inside scanned books. Wrap in double quotes for an exact-phrase match (e.g., "the spice must flow"); unquoted terms match independently and return far broader results.
`offset`	No	Zero-based offset for pagination.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`total`	No	Total matching Internet Archive items across all pages.
`notice`	No	Guidance when the page is empty (how to broaden a query that matched nothing, or which offset to retry when offset ran past the end) or when the text output capped a per-item snippet list. Absent when neither applies.
`offset`	No	Zero-based offset of the first returned match.
`matches`	No	Matching items, up to limit, ordered by relevance.
`totalCount`	No	Total matching items across all pages — the upstream match count, reported even when this page is empty because offset ran past the end.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 24, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode."New value: +"Machine-readable failure mode. Declared by this tool: `upstream_unavailable`: Open Library's full-text search answered HTTP 200 without a result set — no hits object carrying a total. Other values are possible when a failure originates below the handler."

addedOutput schema / properties / error / properties / data / properties / reason / examples
```
Added value: +[
+  "upstream_unavailable"
+]
```

Changed6 schema fields changedAug 25, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "total",
+      "offset",
+      "matches"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode.",
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "total",
-  "offset",
-  "matches"
-]

AddedJul 26, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations provide readOnlyHint and openWorldHint, but the description adds significant behavioral context: the index is 'far slower than the metadata endpoints' and takes 10–30 seconds, and results key on Internet Archive items rather than Open Library works. These details go beyond annotations and help set expectations for latency and result semantics. No contradiction exists.

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?

The description is dense but well-organized: purpose first, then usage, performance, and alternative routing. Every sentence contributes information—no filler. It is a bit long but justified by the complexity of the tool's behavior (exact-phrase syntax, IA vs OL item distinction, speed caveat). Front-loading the core purpose and differentiation is effective.

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

Completeness5/5

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

Given the output schema (not shown but present) and annotations covering readOnly and openWorld, the description is complete for agent use. It covers what the tool does, how to phrase queries, what results look like (IA items with snippets and relevance), how to connect to catalogue records, and performance expectations. Nothing an agent needs to call it correctly is missing.

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?

The schema already describes all three parameters (100% coverage), but the description adds value beyond that. It explains that quoting in query yields exact-phrase matches and unquoted terms match independently, and advises on limit values ('prefer 10–20') because larger responses grow quickly. These are practical details not in the schema, so the description meaningfully enhances parameter understanding.

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?

The description clearly states the tool performs full-text search within scanned books, using the exact phrase 'Search the full text of books scanned by the Internet Archive'. It explicitly differentiates from sibling tools by calling it 'the metadata tools cannot answer' and names openlibrary_search_books as the alternative for metadata queries, so an agent can immediately tell it apart.

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?

Explicit when-to-use guidance is given: 'Use it when the passage is the question, and use openlibrary_search_books to search by title, author, or subject.' It also explains how to chain results to the catalogue via ia_identifier, and notes performance expectations (10–30 seconds). This is clear, actionable direction with alternatives and exclusions.

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

All openlibrary-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.