// SCAN REPORT

Lyceum

30 tools. 13 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

13 can modify or destroy data

17 read-only

30 tools total

Community server · catalogue entry verified 03/07/2026

How to control Lyceum ↓

TOOL MAP

What Lyceum exposes to your agents

Read (17) Write / Execute (10) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Lyceum tools

Destructive · High remove_book The tool permanently deletes books from a library with no undo capability. Destructive · High remove_device This tool deletes a device configuration from the Calibre library system. Destructive · High remove_format Removing a file format from a book is an irreversible deletion of that format's data. Execute · Medium convert_book Converting a book triggers an external operation (format conversion via Calibre content server over HTTP) whose effects depend on arguments.

13 of Lyceum's 30 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Lyceum

PolicyLayer is an MCP gateway — it sits between your AI agents and Lyceum, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "remove_book": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_device": {
    "limits": [
      {
        "counter": "add_device_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "fetch_metadata": {
    "limits": [
      {
        "counter": "fetch_metadata_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Lyceum — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LYCEUM →

Instant setup, no code required.

FULL CATALOGUE

All 30 Lyceum tools

DESTRUCTIVE 3 tools

Destructive remove_book Permanently remove one or more books from the library. This cannot be undone. Destructive remove_device Remove a configured e-reader device. Destructive remove_format Remove one or more file formats from a book (e.g. remove the MOBI copy but keep EPUB).

EXECUTE 3 tools

Execute convert_book Convert a book to a different format (e.g. EPUB to MOBI). This may take a few minutes. Execute send_to_device Send a book to an e-reader device. Downloads the book from the library and sends it to the specified device. Execute send_url_to_device Fetch a URL, convert the article to an epub, and send it directly to an e-reader device without saving to the

WRITE 7 tools

Write add_device Start adding an e-reader device. For Boox: params should include email and optionally region (us, eu, or cn, d Write create_book_from_url Fetch a URL and create an epub book from the article content, adding it to the library. Write mark_read Mark a book as read (or unread) in the library. Optionally provide a date; defaults to today. Pass read: false Write set_cover Set a book Write set_kosync_settings Configure KOSync settings. Set enabled, username, and/or password for KOReader reading progress sync. Write set_metadata Update metadata fields on a book in the library. Fields can include: title, authors (as array), tags (as array Write set_opds_settings Configure OPDS catalog settings. Set enabled, username, and/or password for OPDS Basic Auth. Reader apps use t

READ 17 tools

Read fetch_metadata Search online for book metadata by title, author, or ISBN. Returns multiple results from Google Books that the Read get_add_format_link Get a temporary link to upload an additional format (e.g. EPUB, MOBI, PDF) to an existing book. Returns a sign Read get_book Get full details for a specific book by ID, including authors, tags, series, formats, and description. Read get_download_link Get a temporary download link for a book file. Returns a signed URL that expires in 5 minutes. Read get_kosync_settings Get current KOSync (KOReader reading progress sync) settings. Read get_opds_settings Get current OPDS catalog settings (enabled status, username, catalog URL). Read get_upload_link Get a temporary upload link to add a book to the library. Returns a signed URL that opens a file upload form i Read get_view_link Get a temporary link to view a book Read list_authors List all authors in the library with book counts. Read list_books List books in the library, sorted by most recently added. Read list_books_by_author List all books by a specific author. Read list_books_by_series List all books in a series, ordered by series index. The series_id can be found in the series_id field of any Read list_devices List all configured e-reader devices. Read list_series List all series in the library with book counts. Each result includes the series name and count. To get books Read search_books Search books by title, author, tag, or series name. Supports search syntax (e.g. author:Asimov, tag:sci-fi). Read verify_device Complete device setup. For Boox/Xteink: provide the verification code or device selection. For CrossPoint: pro

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Lyceum

Can an AI agent delete data through the Lyceum MCP server? +

Yes. The Lyceum server exposes 3 destructive tools including remove_book, remove_device, remove_format. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Lyceum? +

The Lyceum server has 7 write tools including add_device, create_book_from_url, mark_read. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Lyceum.

How many tools does the Lyceum MCP server expose? +

30 tools across 3 categories: Destructive, Read, Write. 17 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Lyceum? +

Register the Lyceum MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Lyceum tool call.

Deterministic rules across all 30 Lyceum tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LYCEUM →

Instant setup, no code required.

30 Lyceum tools catalogued and risk-classified — across an index of 43,000+ MCP servers.