liseur-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host for HTTP listener | 127.0.0.1 |
| MCP_PATH | No | Path for HTTP listener | /mcp |
| MCP_PORT | No | Port for HTTP listener | 8000 |
| LISEUR_URL | Yes | Base URL of the instance | |
| LISEUR_TOKEN | No | Device token secret | |
| MCP_TRANSPORT | No | Transport mode: stdio or streamable-http | stdio |
| MCP_AUTH_TOKEN | No | Bearer token for HTTP transport (required when MCP_TRANSPORT=streamable-http) | |
| LISEUR_TOKEN_FILE | No | Path to file containing device token secret | |
| MCP_ALLOWED_HOSTS | No | Allowed Host headers for HTTP transport | localhost |
| MCP_AUTH_TOKEN_FILE | No | Path to file containing bearer token for HTTP transport | |
| LISEUR_TIMEOUT_SECONDS | No | Upstream request timeout in seconds | 30 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_foldersA | List the library folders this account can read. |
| list_booksA | List books in one folder. |
| search_booksA | Search titles, descriptions, series, contributors and tags. |
| get_bookA | Fetch one catalog record by book_id (same shape list_books returns). |
| reading_statsA | Reading totals, streak and pace over a span, plus per-work rows. |
| list_highlightsA | List highlights, notes and bookmarks. |
| get_book_textA | Read the text of a book, one chapter at a time. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool maps to a distinct resource or action: folders, catalog records, book lists, search, stats, highlights, and full text. Even the similarly named get_book and get_book_text are clearly separated by descriptions (metadata vs. chapter text).
Most tools follow a verb_noun snake_case pattern (list_books, search_books, get_book_text). reading_stats is the one outlier as a noun phrase, so the pattern is not perfectly uniform.
Seven tools is a well-scoped size for a reading/librarian server. Each tool covers a meaningful part of the workflow without redundancy.
The surface covers discovery, metadata, text access, highlights, and reading statistics, which are the core read-only operations. Minor gaps exist around pagination/limits for large catalogs or highlight lists, but agents can usually work around them.