Skip to main content
Glama

ampache_library

Read-only

Browse, search, and inspect Ampache artists, albums, songs, genres, labels, licenses, folders, and stats; fetch song stream URLs without media downloads. Writes require confirm=true and writes enabled.

Instructions

Artists, albums, songs, genres, labels, licenses, search, advanced search, stats, folders, and song stream URLs. Media bytes are never downloaded. Writes run only when confirm is true and AMPACHE_ALLOW_WRITES=true. List actions default to offset 0 and limit 25 (max 500). Actions: advanced_search, album, album_disk, album_disk_songs, album_disks, album_songs, albums, artist, artist_albums, artist_songs, artists, folders, genre, genre_albums, genre_artists, genre_songs, genres, get_similar, label, label_artists, labels, license, license_songs, licenses, search, search_group, search_rules, song, song_tags, songs, stats, url_to_song.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "ampache_library"
  }
}

Input Schema

NameRequiredDescriptionDefault
addNo
urlNo
condNo
sortNo
typeNo
exactNo
limitNo
rulesNo
top50No
actionYesAmpache operation to call.
filterNo
offsetNo
randomNo
rule_1No
updateNo
catalogNo
confirmNoBoolean true runs the write when AMPACHE_ALLOW_WRITES is true. Omit it or pass false for a dry-run preview that sends nothing. The string true is rejected.
includeNo
user_idNo
operatorNo
usernameNo
album_artistNo
rule_1_inputNo
rule_1_operatorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.4/5.0
Behavior2/5

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

Valuable behavior is disclosed beyond the annotations: media bytes are never downloaded, list actions default to offset 0 / limit 25 with a max of 500, and confirm=false acts as a dry-run preview that sends nothing. However, the statement 'Writes run only when confirm is true and AMPACHE_ALLOW_WRITES=true' describes a capability to mutate state, while the annotations declare readOnlyHint=true and the action enum contains no write actions — a conflicting signal an agent must resolve. The useful pagination, dry-run, and no-download facts keep this above the floor, but the read/write inconsistency is a real defect.

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

Conciseness3/5

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

The first three sentences are dense and front-loaded with scope and safety facts, but the trailing alphabetized action list restates the schema enum verbatim and consumes most of the description's length without adding routing value. Splitting behavior notes from a redundant enumeration would make the useful content easier to find.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 24-parameter, nested-object tool with no output schema, the description gives a map of the domain but not enough to correctly construct most calls — nothing explains how filter/type/cond/rules/operator combine for search or advanced_search, or what 'type' means for the resource actions. Given the tool's complexity and 8% schema coverage, key operational knowledge is missing.

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

Parameters2/5

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

Schema description coverage is only 8%, so the description carries the burden and mostly does not: roughly twenty parameters (add, url, cond, sort, type, exact, rules, top50, filter, random, rule_1, rule_1_input, rule_1_operator, update, catalog, include, user_id, operator, username, album_artist) get no meaning from either source. It does contribute the non-schema defaults for offset/limit and clarifies that the string 'true' is rejected for confirm, but it explains none of the search/rule parameters that advanced_search and search_group depend on.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the resource families the tool touches (artists, albums, songs, genres, labels, licenses, search, stats, folders, stream URLs), which separates it from siblings like ampache_playlists and ampache_catalogs, but it never states a verb or summarizes what a call actually does. With 32 heterogeneous actions and no framing sentence such as 'read metadata from the Ampache music library', an agent must infer the purpose from the enum. 'Media bytes are never downloaded' is the one genuinely clarifying scope statement.

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

Usage Guidelines2/5

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

No guidance on when to choose this tool over a sibling, and no per-action routing hints (e.g. when to use album_songs vs songs with a filter, or search vs advanced_search). The only usage-like content is mechanical: when writes are permitted and what the pagination defaults are. An agent still has to guess for most of the 32 actions.

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