# THIRI Chord Intelligence MCP server

Deterministic music theory for agents: analyze, voice, reharmonize, conduct — computed, not guessed

## Links
- Registry page: https://www.getdrio.com/mcp/ai-thiri-chord-intelligence
- Repository: https://github.com/BluesPrince/thiri-mcp
- Website: https://thiri.ai

## Install
- Command: `npx -y @bluesprincemedia/thiri-mcp`
- Endpoint: https://mcp.thiri.ai/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Package: Npm @bluesprincemedia/thiri-mcp v0.5.2
- Environment variable: THIRI_API_KEY (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.thiri.ai/mcp

## Tools
- analyze_chord - Parse a chord into root, quality, intervals, and (with a key) roman numeral + function. Endpoint: https://mcp.thiri.ai/mcp
- resolve_chord - Resolve a chord to spelled notes, frequencies, MIDI, and recommended scales. Endpoint: https://mcp.thiri.ai/mcp
- generate_voicing - Instrument-ready voicing in a style; pass previousNotes for a voice-leading score. Endpoint: https://mcp.thiri.ai/mcp
- reharmonize - Reharmonize a progression. Techniques: tritone_sub, ii_v_insertion, modal_interchange, diminished_passing, secondary_dominant, chain_of_dominants, coltrane_changes, backdoor (or auto). Endpoint: https://mcp.thiri.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: ai.thiri
- Version: 0.5.2
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Aug 1, 2026
- Source: https://registry.modelcontextprotocol.io