Skip to main content
Glama
arr-mcps

komga-mcp

by arr-mcps
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

komga_books

Handle Komga book operations: retrieve details, search with filters, update metadata, track read progress, list duplicates, and access nearby books.

Instructions

komga books operations on Komga. Pass operation and an arguments dict matching that operation's parameters.

  • analyze_book(book_id) — Analyze a book. Requires ADMIN.

  • get_book(book_id) — Get book details, media information, metadata, and read progress.

  • get_book_next(book_id) — Get the next book in the series.

  • get_book_pages(book_id) — List page metadata for a book without downloading page images.

  • get_book_previous(book_id) — Get the previous book in the series.

  • get_book_readlists(book_id) — List readlists containing a book.

  • get_books_ondeck(library_id=None, page=0, size=50, sort=None, unpaged=False) — List books currently on deck for the authenticated user.

  • get_duplicate_books(page=0, size=50, sort=None, unpaged=False) — List duplicate books by file hash. Requires ADMIN.

  • get_latest_books(library_id=None, page=0, size=50, sort=None, unpaged=False) — List recently added or updated books.

  • list_book_thumbnails(book_id) — List thumbnail metadata for a book; does not download image bytes.

  • mark_book_unread(book_id) — Mark a book as unread.

  • refresh_book_metadata(book_id) — Re-import embedded metadata for a book. Requires ADMIN.

  • search_books(full_text='', condition=None, page=0, size=50, sort=None, unpaged=False) — Search books using Komga's BookSearch body. Structured condition leaves are keyed by fields such as libraryId, collectionId, title, tag, genre, publisher, language, ageRating, readStatus, seriesStatus, mediaStatus, author, deleted, complete, oneShot, releaseDate, numberSort, and seriesId. Each leaf contains an operator object. Use string operators is, isNot, beginsWith, doesNotBeginWith, contains, doesNotContain, endsWith, or doesNotEndWith; booleans use isTrue/isFalse; dates use after/before/isInTheLast/isNotInTheLast/isNull/isNotNull; and group conditions with anyOf (OR) or allOf (AND). Read-status values are UNREAD, READ, IN_PROGRESS; media-status values are UNKNOWN, ERROR, READY, UNSUPPORTED, OUTDATED; series-status values are ENDED, ONGOING, ABANDONED, HIATUS.

  • set_book_read_progress(book_id, page=None, completed=None) — Set a book's read position. Supply page and/or completed.

  • update_book_metadata(book_id, patch) — Update book metadata; null unsets a field and omission keeps it. Requires ADMIN.

  • update_books_metadata_bulk(updates) — Bulk update book metadata using a map of book ID to patch. Requires ADMIN.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argumentsNo
operationYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Install Server

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries full responsibility for disclosing behaviors. It explicitly notes permissions (ADMIN for some ops), side-effect semantics for updates ('null unsets a field'), and non-downloading behaviors for page/thumbnail listing. It also explains the arguments structure and search syntax, covering edge cases like nullable arguments.

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

Conciseness5/5

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

The description is front-loaded with the general invocation pattern, then presents a well-organized bullet list of operations with minimal but sufficient detail. Each line is concise and information-dense, avoiding redundancy while covering 16 distinct operations.

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 tool's complexity (16 operations, varied parameters, permissions, rich search conditions), the description is exceptionally complete. It details permissions, null handling, and search operator semantics. Since an output schema exists, lack of return-value descriptions is acceptable.

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

Parameters5/5

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

The input schema only defines `operation` (enum) and a generic `arguments` object with 0% coverage. The description fully compensates by enumerating every operation's parameters, defaults, and types (e.g., 'page=0, size=50'). This is essential for correct tool use and is provided comprehensively.

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 it performs 'komga books operations on Komga' and lists all 16 supported operations with specific verbs and targets (e.g., 'get_book_next', 'search_books'). It distinguishes from sibling tools by focusing exclusively on books, and the operation list makes the tool's scope unambiguous.

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

Usage Guidelines4/5

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

The description provides clear guidance on how to invoke the tool (pass operation + arguments dict) and details each operation's parameters and required permissions (e.g., 'Requires ADMIN'). However, it does not explicitly mention when not to use this tool or contrast with sibling tools, though the separation is obvious from naming.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/arr-mcps/komga-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server