Skip to main content
Glama
Sign In
lyricmood-mcp

lyricmood-mcp

by yigitates17
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Find Similar By Lyrics

find_similar_by_lyrics

Find songs with lyrics that discuss similar themes as a given track—across languages—and rank candidates by lyrical meaning.

Instructions

Find songs whose lyrics are about similar things as the given song (works across languages). Candidates come from Last.fm (similar tracks, tags, similar artists) and ReccoBeats, and are ranked by lyrics meaning with a local multilingual model. Scores are 0-1 relative to this search, not absolute. matching_lines shows the passages that matched best; use them to explain the connection. The first search for a song can take ~30-60 s; repeats are fast.

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": {
      "track": "<track>"
    },
    "name": "find_similar_by_lyrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoHow many results (1-25).
trackYesThe song: a Spotify track ID/URL/URI (best: use `id` from search_track) or free text like "Carnival of Rust Poets of the Fall".
expand_poolNoTrue: gather fresh candidates from Last.fm and ReccoBeats (slow the first time, cached after). False: rank only songs analyzed in earlier searches (instant, no network).
mood_weightNo0 = lyrics only. Raise (e.g. 0.3) to also prefer songs with similar musical mood (valence/energy). Use when the user cares how it sounds, not just what it says.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses the candidate sources (Last.fm similar tracks/tags/artists, ReccoBeats), the ranking mechanism (local multilingual model), latency behavior (~30-60 s cold, fast on repeats), and the non-absolute nature of the 0-1 scores. It also explains how to interpret and use matching_lines in the response.

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

Conciseness5/5

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

Purpose and the cross-language capability are front-loaded, followed by sourcing, scoring semantics, and latency expectations in that order. Every sentence carries distinct information an agent needs, with no restatement of the name or title.

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

Completeness4/5

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

No output schema exists, so the description must cover returns; it names scores and matching_lines but not the remaining result fields, and it says nothing about failure behavior for unrecognized tracks. For a four-parameter search tool, though, it is otherwise complete enough to invoke correctly on the first try.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline is 3, but the description adds real cross-cutting meaning: it ties expand_pool to the cold-start latency, explains that scores are relative to this specific search, and clarifies the tradeoff encoded by mood_weight. The track parameter's format detail lives mostly in the schema, which keeps this from a 5.

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

Purpose5/5

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

States a specific verb and resource (find songs by lyric meaning) plus a distinguishing capability (cross-language semantic matching) that separates it from siblings like get_lyrics and search_track. The scope is unambiguous and an agent can route to it without opening the schema.

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

Usage Guidelines4/5

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

Gives concrete selection guidance for the optional parameters: raise mood_weight 'when the user cares how it sounds, not just what it says', and use expand_pool=false for instant cache-only ranking. It does not name an explicit alternative sibling or state when-not-to-use, so it falls short of full routing guidance.

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

Deploy Server

Other Tools