zlib-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| zlib_searchA | Search z-library for books. Returns a trimmed list — each entry carries the "id" and "hash" that zlib_get_download_url and zlib_download require, plus title/author/year/language/extension/size. Present the candidates to the user and let them pick before downloading anything. |
| zlib_get_download_urlA | Get a direct download URL for one book. Requires the "id" and "hash" from a zlib_search result. The link is short-lived and tied to the session that fetched it — use it right away, never cache or reuse it. Fetching a link consumes one unit of the account's daily download allowance (see zlib_limits). This server cannot save files to disk: set the ZLIB_DOWNLOAD_DIR environment variable in the MCP client config to a directory you want downloads written to, then restart the server to enable zlib_download. |
| zlib_limitsA | Check the z-library account's daily download allowance: how many downloads were used today, the daily cap, and how many remain. Call this before a batch of downloads, or when a download fails with a quota error. Takes no arguments and does not consume any allowance. |
| zlib_loginA | Exchange a z-library email + password for the long-lived remix credentials (remix_id / remix_key). This is a one-time setup helper, not a per-call login: put the returned values into your MCP client config as ZLIB_REMIX_ID and ZLIB_REMIX_KEY, then restart the server. The password is never stored, logged, or returned. Do not call this before every search. |
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 4 tools
Each tool has a distinct purpose: search for books, fetch download URLs, check account limits, and handle login. No two tools overlap in functionality, making selection unambiguous.
All tools share the 'zlib_' prefix and most follow a verb-based pattern (search, get_download_url, login), but 'limits' is a noun rather than a verb like 'get_limits' or 'check_limits'. Minor deviation but still coherent.
With 4 tools covering search, URL generation, quota checking, and authentication, the set is well-scoped for a focused book download workflow. No redundant tools, and each one earns its place.
The descriptions repeatedly mention a 'zlib_download' tool and instructions for enabling it, but that tool is not included in the provided set. This leaves a critical gap in the core workflow, preventing actual file downloads.