THIRI Chord Intelligence β Music Theory MCP Server
# π· THIRI Chord Intelligence β MCP Server
[](https://www.npmjs.com/package/@bluesprincemedia/thiri-mcp)
[](https://www.npmjs.com/package/@bluesprincemedia/thiri-mcp)
[](https://github.com/BluesPrince/thiri-mcp/actions/workflows/ci.yml)
[](./LICENSE)

[](https://glama.ai/mcp/servers/BluesPrince/thiri-mcp)
**Give your AI real music theory.** THIRI is the deterministic **music theory MCP server + API** for AI builders β it lets Claude, Cursor, or any [MCP](https://modelcontextprotocol.io) agent **analyze chords, run roman-numeral analysis, generate voicings, and reharmonize progressions** with answers that are *computed, not guessed*.
LLMs hallucinate music theory: wrong notes, fake roman numerals, voicings that don't voice-lead. THIRI is a **deterministic** engine (pitch-class-set theory over β€/12) behind a hosted API β so `C7sus4` keeps its suspension, `Caug` spells `C E G#`, and "Coltrane changes on Dm7 G7 Cmaj7" returns `Cmaj7 Ab7 Abmaj7 E7`, every time.
**Downstream of Suno / Udio or any generator?** Wrap the output and get a correct chord chart your agent can trust. And unlike `tonal.js` or `music21`, THIRI is hosted and agent-native (no install, any language) β and it *reharmonizes* and *voice-leads*, not just looks chords up.
> β If this is useful, star the repo β it helps other musicians and agent builders find it.
> π₯ **Join the First 55 AI Music Builders**: Want elevated rate limits (300 req/min), direct founder support, and early access to upcoming tools? Join our developer community on **[Skool β Blues People AI](https://www.skool.com/blues-people-ai-4513/about)**.
## Musicians: 2-minute setup (no code)
1. Get a free key at **[build.thiri.ai/developers](https://build.thiri.ai/developers)**
2. In **Claude**: Settings β **Connectors** β **Add custom connector** β URL `https://mcp.thiri.ai/mcp` β paste your `sk_live_` key
3. Ask Claude: *"Reharmonize Dm7 G7 Cmaj7 with Coltrane changes."*
That's it β no install, no config file. Builders: full install options (Claude Code, Desktop config, raw HTTP) are [below](#install).
## What you can ask
> *"Analyze Dm7b5 in C."* β `iiΓΈ7`, half-diminished, borrowed predominant, + scale options
> *"What notes are in C7sus4?"* β `C F G Bb` (the suspension survives)
> *"Give me a rootless Cmaj7 voicing, then voice-lead into Dm7."* β voicings + a voice-leading score
> *"Reharmonize Dm7 G7 Cmaj7 with Coltrane changes."* β `Cmaj7 Ab7 Abmaj7 E7`
## Tools
| Tool | What it does |
|------|-------------|
| `analyze_chord` | Chord β root, quality, intervals, roman numeral & harmonic function (secondary dominants, modal-interchange labels) |
| `resolve_chord` | Chord β spelled notes (enharmonically correct), frequencies, MIDI, scale recommendations |
| `generate_voicing` | Instrument-ready voicings (rootless/bill_evans, shell, triad, pad, guide-tones, drop-2/3); pass `previousNotes` for a **voice-leading score**; `colorPreferences` for explicit tensions |
| `reharmonize` | Progression reharmonization β 8 techniques: `tritone_sub`, `ii_v_insertion`, `modal_interchange`, `diminished_passing`, `secondary_dominant`, `chain_of_dominants`, `coltrane_changes`, `backdoor` (or `auto`) |
| `conduct_band` | Natural-language band conduct β lanes + MIDI (hosted MCP v0.3+) |
> Runs on the **v2 grid engine** β correct sus chords, real triads, enharmonic spelling, all altered dominants β with request timeouts, quota reporting, and structured errors.
### Conductor & composition companions (Desktop only)
For **hear-it** agent loops (conduct β server-side render β WAV through your speakers), add a second local server alongside hosted theory tools:
```json
{
"mcpServers": {
"thiri": {
"command": "npx",
"args": ["-y", "@bluesprincemedia/thiri-mcp"],
"env": { "THIRI_API_KEY": "sk_live_your_key" }
},
"thiri-conductor": {
"command": "npx",
"args": ["-y", "@bluesprincemedia/thiri-mcp", "thiri-conductor-mcp"],
"env": { "THIRI_API_KEY": "sk_live_your_key" }
},
"thiri-composition": {
"command": "npx",
"args": ["-y", "@bluesprincemedia/thiri-mcp", "thiri-composition-mcp"]
}
}
}
```
| Bin | Tools |
|-----|-------|
| `thiri-conductor-mcp` | `conduct_band`, `render_audio` (server-side Csound via `POST /v2/render`), `play_audio`, `search_corpus` |
| `thiri-composition-mcp` | Composition IR tools + `play_composition` (fluidsynth preview) |
Rendering runs **server-side** as of v0.5.0 β no Csound install needed. Proof: `npm run test:conductor` Β· live docs: [build.thiri.ai/lab/conductor-mcp](https://build.thiri.ai/lab/conductor-mcp) Β· [agent recipes](https://build.thiri.ai/lab/agent-recipes).
### Conductor Agent (vibe compose)
End-to-end persona for local vibe composition β skill, CLI, and Band dashboard panel:
| Entry | Command / path |
|-------|----------------|
| **Cursor skill** | Copy `THIRI/lab/skills/thiri-conductor-agent/SKILL.md` β `~/.cursor/skills/thiri-conductor-agent/SKILL.md` |
| **CLI** | `cd thiri-mcp && npm run conductor:vibe -- "gospel ballad in F minor"` |
| **Dashboard** | `npm run dev:studio` β [localhost:5173/band](http://localhost:5173/band) β **Vibe Conduct** panel |
| **Lab proof** | [build.thiri.ai/lab/conductor-agent](https://build.thiri.ai/lab/conductor-agent) |
Dual MCP config above + `mapConductResultToStudioModules` after each `conduct_band`. Last CLI render writes `~/.thiri/conductor-last.json` (local only, not committed).
### Flagship agent recipe (analyze β conduct β render β critique)
Paste in order after dual MCP config above:
1. **Analyze** β *"Analyze Dm7 G7 Cmaj7 in key C with analyze_chord; summarize roman numerals and tension."*
2. **Conduct** β *"conduct_band: warm Rhodes pad, walking bass, brush drums, 8 bars medium swing in C."*
3. **Render** β *"render_audio from the conduct result at tempo 120."*
4. **Critique** β *"play_audio; critique voice-leading and register balance; suggest one revision."*
Full prompts: [build.thiri.ai/lab/agent-recipes](https://build.thiri.ai/lab/agent-recipes)
### Hosted vs local boundary
| Surface | Audio render |
|---------|--------------|
| `mcp.thiri.ai` / hosted connector | No β theory + `conduct_band` lanes only |
| Local `thiri-conductor-mcp` | Yes β WAV rendered server-side (`POST /v2/render`), played locally; no Csound install needed |
## Install
Get a free key at **[build.thiri.ai/developers](https://build.thiri.ai/developers)**, then pick a path:
**Claude Desktop / web / mobile β hosted (one-click custom connector, nothing to install):**
Settings β Connectors β **Add custom connector** β URL `https://mcp.thiri.ai/mcp` β paste your `sk_live_` key on the consent page. Same 5 tools, same key, same quota β no config file, no `npx`.
**Claude Code (one line):**
```sh
claude mcp add thiri --env THIRI_API_KEY=sk_live_your_key -- npx -y @bluesprincemedia/thiri-mcp
```
**Claude Desktop** (`claude_desktop_config.json`):
```json
{
"mcpServers": {
"thiri": {
"command": "npx",
"args": ["-y", "@bluesprincemedia/thiri-mcp"],
"env": { "THIRI_API_KEY": "sk_live_your_key" }
}
}
}
```
## Prefer raw HTTP? (no MCP needed)
The same engine is a plain REST API:
```sh
curl -X POST https://chords.thiri.ai/v2/analyze \
-H "Authorization: Bearer YOUR_KEY" -H "content-type: application/json" \
-d '{"chord":"Dm7b5","key":"C"}'
```
Five endpoints: `/v2/analyze`, `/v2/resolve`, `/v2/voicing`, `/v2/reharmonize`, `/v2/conduct`. See [`openapi.yaml`](./openapi.yaml).
## Environment variables
| Variable | Default | Description |
|----------|---------|-------------|
| `THIRI_API_KEY` | (none) | Bearer token (`sk_live_β¦`) β get one at build.thiri.ai/developers |
| `THIRI_API_URL` | `https://chords.thiri.ai` | API base (override only for local dev) |
## Development
```sh
npm install && npm run build && npm start
```
## License
**PolyForm Noncommercial 1.0.0** β Β© 2026 Blues Prince Media. Free for personal,
research, and noncommercial use; commercial use requires a license
(dennison@bluesprincemedia.com). See [`LICENSE`](./LICENSE). Versions published at or
before v0.5.0 remain under the MIT/PolyForm dual license they shipped with.
> As of v0.5.0 the composition engine and Csound renderer run server-side behind
> the hosted API (`POST /v2/compose`, `POST /v2/render`); their source no longer
> ships in this package.
TDQS
Scored across 5 tools
Each tool targets a distinct musical operation: resolving, analyzing, voicing, reharmonizing, and arranging. The only mild overlap is between resolve_chord and analyze_chord, since both accept chord symbols, but their output purposes are clearly separated by the descriptions.
Four of five tools follow a clear verb_noun pattern (resolve_chord, analyze_chord, generate_voicing, conduct_band). The exception is reharmonize, which is a single verb without an explicit object, but it is still recognizable and does not create confusion.
Five tools is well-scoped for a specialized music theory server. Each tool addresses a distinct and meaningful part of chord intelligence, from analysis and resolution to voicing, reharmonization, and full band arrangement.
The tool surface covers the core chord intelligence workflow: parse/analyze chords, resolve them to concrete musical data, generate voicings with voice-leading support, reharmonize progressions, and produce a full arrangement. There are no obvious dead ends or missing essential operations for the stated domain.