Calibre MCP server
io.github.caelum29/calibre-mcp·v0.12.0·22 starsCalibre ebook library server: search, read content, curate metadata, semantic search, gated writes.
22 stars1.1k downloads/wk
Reviews
Write oneNobody has reviewed Calibre yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Calibre tools (21, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
calibre_add_bookImport a local ebook file (EPUB/PDF/MOBI/…) into the library. The file must live under an
calibre_board_dataInternal endpoint for the in-chat cover-board widget. Returns the cached payload of a
calibre_build_indexBuild the semantic index for specific books (required: bookId, ids, or query — full-library indexing is deferred). A query selects ALL matching books (no 100-book cap); large selections run long and may outlive the client timeout — re-run the same call to resume, since up-to-date books are skipped. Extracts, chunks, and embeds each book. Set keywordOnly=true (or when the embedding model is absent,
calibre_bulk_updatewrite actionApply the same metadata changes (tags, series, publisher, etc.) to a set of books selected
calibre_extract_isbnOffline scan of a book's own text for a checksum-valid ISBN → sets identifiers:isbn
calibre_find_duplicatesFind probable duplicate books. mode=identical (exact title+authors) or similar (fuzzy) group the library (or ids/query/filter subset — filter takes a bundle name) with a merge-safety score; mode=compare diffs 2+ ids field-by-field. Read-only — never merges.
calibre_get_bookGet full metadata (authors, ISBN, formats, comments, cover) for one book by its id or uuid (id and bookId are interchangeable — pass the bookId from a search result). Set include_cover=true only when the cover image itself must be inspected.
calibre_get_contentExtract a book's text as a capped, fenced excerpt; pass the returned nextCursor token verbatim to walk the whole book, or jump to a char position with offset (e.g. a search passage's charStart). Set structure=true for a chapter map with per-chapter cursors. To find text inside a book, use calibre_search scope=book.
calibre_get_figuresList a book's figures — images the text references, identified by caption (Figure 1-2 / Рис. 3.1) — with page + caption per figure, then fetch chosen ones as images via indexes (≤3 per call). Captions let you pick figures before spending image tokens. In MCP Apps hosts the fetched figures also render for the user in an in-chat viewer, so you can point at them by figure number — but describe only w
calibre_list_categoriesBrowse library categories (Authors, Tags, Series, Languages, Publisher). No field → list the categories; with a field → its values + counts, filterable via a valueFilter regex (case-insensitive by default; a leading inline flag like `(?i)` is accepted).
calibre_list_librariesList the Calibre libraries available on the Content Server and which one is the default. Call this first to discover valid library names.
calibre_manage_bundlesList, create, update or delete Bundles — named topical filters backed by Calibre saved
calibre_merge_booksMerge duplicate book records: moves formats from source books into a target (target's copy
calibre_open_bookInternal endpoint for the in-chat widgets' Open button. Launches a book in the local
calibre_pingHealth check: confirms the MCP server can reach the running Calibre
calibre_quality_reportScan books for metadata problems: missing fields, raw-filename titles, invalid ISBNs, author-sort mismatches, series gaps. Defaults to the whole library; narrow with ids/query/filter (a bundle name) or specific checks. Read-only.
calibre_recover_metadataPropose real metadata for a book with a missing/raw-filename title via online provider lookup (ISBN from its identifiers or text, else title/author) on Open Library and Google Books. Preview only — returns a changes object for calibre_update_book; never writes.
calibre_remove_bookwrite actionRemove books from the library. Removed books go to Calibre's Trash and can be restored from
calibre_searchFind books by exact title, author, ISBN, tag, or Calibre query syntax (mode=meta), or by full text (mode=fts). scope=book returns short keyword snippets from inside one book; first hits often land in TOC/front matter — for definitional or topic questions within a book prefer calibre_semantic_search scope=book (ranked passages with char offsets). Use calibre_semantic_search for meaning/topic querie
calibre_semantic_searchMeaning-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 keywo
calibre_update_bookwrite actionReplace metadata fields on one book (title, authors, tags, series, rating, identifiers, comments, or any #custom column). Omitted fields are untouched. Requires writes to be enabled.
Public scan report
scanner v0.1.10 · 2026-11-02 · same rubric, same numbers if you re-run it
- Code scan225 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- mediumeval / new Function used
exec.evaldist/semantic/store.js: …une these // ONLY through the retrieval eval (test/eval/retrieval), never by feel. con…
How Calibre compares
Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 85/100
- higher than 75% of 3,472 Web search servers
- Tools
- 21
- the typical Web search server has 5
- Tools that change things
- 14%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 22
- more than 90% of 1,783 Web search servers
- Downloads a week
- 1,129
- more than 95% of 816 Web search servers with a package
What its tools let an agent do: 18 read · 3 change
Release history: 5 versions in the registry since 2026-08-21, latest 2026-10-30, typically one every 4 days.
Install Calibre in Claude Code, Cursor or VS Code
Runs npx -y calibre-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add calibre-mcp -- npx -y calibre-mcp
What the publisher says
From the Calibre repository's README, as published. We do not edit it. Read it on GitHub
📚 calibre-mcp
The most capable Calibre MCP server in existence — connect Claude (or any MCP client)
to your Calibre ebook library and search it by meaning, not
just keywords.
Ask your AI assistant “which of my books explain consumer-group rebalancing?” and get the exact chapter — across 800+ books or inside one. Curate metadata, dedupe, and safely edit your library, all through natural language.
One question → semantic search → 3D cover flow → book card → exact passage → figure viewer, all inside Claude Desktop (MCP Apps)
✨ Highlights
and (opt-in) write — update metadata, bulk-edit, merge duplicates, import, delete, and manage bundles (named topical filters).
- 19 tools covering the full surface: search, read content, browse categories, curate,
library or inside a single book. Multilingual (English + Russian verified, cross-lingual queries work). No other Calibre MCP server has this.
- Semantic search — meaning-based, hybrid vector + keyword retrieval over your whole
searches render an interactive cover carousel, calibregetbook a book detail card with cover, rating, and read/similar actions, and calibregetfigures a figure viewer that shows you the same diagrams the assistant fetched. Text-only hosts are unaffected.
- In-chat UI (MCP Apps) — in hosts that support MCP Apps (Claude Desktop), library
and recover real metadata for books with raw filenames (795731065.pdf → Fundamentals of Software Engineering) via Open Library / Google Books.
- Curation tools — find duplicates with merge-safety scoring, audit metadata quality,
operations preview first and require confirmation; all writes route through the Content Server so they never race the Calibre GUI.
- Safe by default — read-only unless you explicitly enable writes; destructive
📋 Requirements
Content server*). Tested against Calibre 9.x; any recent version should work.
- Calibre with the Content Server running (in Calibre: *Connect/share → Start
one-click bundle — Desktop ships its own runtime).
- Node.js ≥ 22.5 for the npm/npx install (not needed for the Claude Desktop
(brew install poppler) or Python 3 with PyMuPDF (pip install pymupdf). Without them the server falls back to Calibre's ebook-convert.
- Optional, for best PDF text extraction: poppler's pdftotext
🚀 Quick start
Easiest — let your agent install it for you
Grab the guided-installer skill and hand the whole job to your agent:
npx skills@latest add caelum29/calibre-mcp # pick calibre-mcp-setupShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-11-02restoreB → Ascore 85: eval / new Function used
Calibre: common questions
- Is Calibre MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the Calibre safety report
- How do I install Calibre?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Calibre need an API key?
- No secret keys are declared. It reads 4 settings from the environment.
- Is Calibre maintained?
- The last commit was in the last day (2026-11-01). The latest release is v0.12.0.
- What can I use instead of Calibre?
- Servers from other publishers that do the same job: Zotero MCP server, Internet Archive MCP server and Zotero MCP server.
- How does Calibre compare with other Web search MCP servers?
- safety score 85/100 (higher than 75% of 3,472 Web search servers); tools 21 (the typical Web search server has 5); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Calibre
Same job from other publishers: the closest match first, then the best rated.
- Zotero MCPSearch your Zotero library, retrieve item metadata, and read full text from AI assistants.not reviewedEstablishedB
- Internet ArchiveSearch the Wayback Machine and IA library (40M+ items), fetch snapshots, item metadata, and text.not reviewedGrowingA
Zotero MCPSearch, read, annotate, and add to your Zotero research library, local or web.not reviewedWidely usedB- ArxivSearch arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.not reviewedWidely usedA
- SocraticodeMCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.not reviewedEstablishedB