Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Music Metadata API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ffreqblog.com%2Ffreqblog" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ffreqblog.com%2Ffreqblog" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Music Metadata API.
Look up a track's audio features by name, ISRC, MusicBrainz ID, or Spotify ID
Extract BPM, key, energy, and more from an uploaded audio file
Identify a recording by its audio fingerprint
Find tracks by BPM or by musical key, including harmonically compatible keys
Discover acoustically similar tracks and build a harmonic radio playlist
GET STARTED
Order a crate into a beat-matched, energy-arced setlist
Bulk-enrich a CSV of artist and title pairs with audio features
Patterns agents use Music Metadata API for, with concrete tasks.
★ Agent-Driven Track Analysis
An AI agent connected through Jentic answers a question about a song by looking it up and returning its BPM, key, energy, and valence, so a product can tag or filter music without a separate analysis step. Because the lookup accepts a name, ISRC, MusicBrainz ID, or Spotify ID, the agent can resolve a track from whatever identifier it already holds.
Look up this track by name and artist and return its BPM, key, energy, and danceability
Audio Feature Extraction
A workflow that holds its own audio extracts features directly by posting the file for analysis, and can fingerprint-identify an unknown recording, so a library gets consistent metadata whether or not the track is already catalogued. The analysis returns the same feature set as the catalog lookups, so downstream logic treats both sources the same way.
Analyze this uploaded audio file and return its BPM, key, and energy, then identify the recording
Harmonic Mixing and Playlists
A DJ or playlist tool builds sets that flow by finding harmonically compatible keys, scoring how well two tracks mix, and ordering a crate into a beat-matched, energy-arced setlist, so a mix holds together without manual key-matching. Radio and next-track endpoints extend a seed into a continuous playlist tuned for harmony and tempo.
Order this crate into a beat-matched, energy-arced set and suggest the next track after the closer
46 endpoints — the music metadata api returns audio features such as bpm, musical key, energy, danceability, and valence for a track, and extracts the same features from an uploaded file, so an application can analyse music without running its own audio pipeline.
METHOD
PATH
DESCRIPTION
/analyze
Extract audio features from an uploaded file
/lookup
Look up a track by name, ISRC, MusicBrainz ID, or Spotify ID
/v1/audio-features/{identifier}
Get Spotify-compatible audio features for a track
/identify
Identify a recording by audio fingerprint
/bpm
Find tracks by BPM
/recommendations
Get recommended tracks for seed tracks
/search
Search the catalog by track, artist, or album
/setlist
Order a crate into a beat-matched set
/analyze
Extract audio features from an uploaded file
/lookup
Look up a track by name, ISRC, MusicBrainz ID, or Spotify ID
/v1/audio-features/{identifier}
Get Spotify-compatible audio features for a track
/identify
Identify a recording by audio fingerprint
/bpm
Find tracks by BPM
/recommendations
Get recommended tracks for seed tracks
/search
Search the catalog by track, artist, or album
/setlist
Order a crate into a beat-matched set
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Music Metadata API by hand means handling X-Api-Key auth and picking the right lookup path for whichever identifier you hold, whether a name, ISRC, MusicBrainz ID, or Spotify ID. Through Jentic you install once, import the Music Metadata API from the API Directory, store the key once, and your agent calls it.
Permission scoping
You choose which operations your agent may call, so you can allow track lookups and audio analysis while leaving webhook configuration out. Rules bound which operations run, so the agent analyses the music you grant and nothing else.
Credential isolation
Your Music Metadata API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get a track's BPM and key' or 'analyze an audio file', and Jentic returns the matching Music Metadata operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Music Metadata API through Jentic.
Is there a Freqblog MCP server?
You don't need an MCP server to give your agent the Music Metadata API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent can look up audio features and analyze audio straight away, with no extra server to run and no tool definitions sitting in the agent's context.
Can I limit what my agent is allowed to do with the Music Metadata API?
Yes. The API is mostly read and analysis operations, so you can write a rule that allows only lookups and feature extraction and leaves webhook changes out. Every call the agent makes is logged, so you can see exactly which tracks it analysed.
What authentication does the Music Metadata API use?
The Music Metadata API authenticates with an API key sent in the X-Api-Key header per its OpenAPI spec. Through Jentic the key is stored encrypted by your own instance and added to each request at call time, so it never appears in the agent's prompt or logs.
Can I use the Music Metadata API as a Spotify audio-features replacement?
Yes. Dedicated endpoints return audio features in a Spotify-compatible shape by identifier, including a batch form, so code written against the deprecated Spotify audio-features endpoint can switch over. You can also look up tracks by ISRC or MusicBrainz ID when you do not have a Spotify ID.
What are the rate limits for the Music Metadata API?
The OpenAPI spec does not state request rate limits for the Music Metadata API. For current limits and fair-use guidance, check the provider documentation at https://freqblog.com.
How do I analyze a track through Jentic?
Import the Music Metadata API from the Jentic API Directory, then have your agent issue a request such as 'get the BPM and key for this track'. Jentic matches the intent to the lookup operation and returns its input schema so the agent builds the correct request, with your stored key injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Look up track audio features by name, ISRC, MusicBrainz ID, or Spotify ID, analyse uploaded audio, and build harmonic setlists in the Music Metadata API. Authenticates with an API key in the X-Api-Key header.
Use for: Look up the BPM and key for a track by name and artist, Get Spotify-shape audio features for a track by its ID, Extract audio features from this uploaded file, Find all catalog tracks around 124 BPM
Not supported: Does not stream audio, host music files, or handle licensing and royalties. Use for audio-feature lookup, analysis, and harmonic-mixing metadata only.
The Music Metadata API returns audio features such as BPM, musical key, energy, danceability, and valence for a track, and extracts the same features from an uploaded file, so an application can analyse music without running its own audio pipeline. You look up a track by name, ISRC, MusicBrainz ID, or Spotify ID, fetch Spotify-shape audio features for compatibility, or analyse and fingerprint-identify your own audio. Catalog, harmonic-mixing, and recommendation endpoints add search by BPM or key, similar-track discovery, radio and setlist building, and bulk enrichment of a CSV of tracks.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>