AI Jam Sessions. Machine learning the old fashioned way.

Reading

Real MIDI sheet music with deep musical annotations — parsed, analyzed, and explained. Not hand-written approximations.

Hearing

Six audio engines play through your speakers so the humans in the room become the AI's ears.

Seeing

Piano roll renders as SVG the model can read back. Interactive guitar tablature. Browser cockpit with visual keyboard.

Remembering

Practice journal persists across sessions. Next time, the AI reads its journal and picks up where it left off.

Singing

Vocal tract synthesis with 20 voice presets. Sing-along mode with solfege, contour, and syllable narration.

41 MCP Tools + 3 Prompts

Learn, play, sing, build, score — browse songs, transpose keys, mute hands, preview teaching cues, render piano rolls, write annotations, and journal reflections.

A Training Dataset to Match

jam-actions-v0 — a public corpus of 115 multi-turn MCP tool-use traces over classical piano, with a 7-axis release gate and cold-start reproducibility. CC-BY-SA-3.0-DE.

115 records · 8 piano pieces

Public subset of the full corpus: 8 classical-piano arrangements from piano-midi.de (Beethoven, Bach, Schubert, Schumann, Mozart, Mendelssohn, Tchaikovsky). 16-record canonical post-repair baseline.

7-axis release gate

Absolute floor, margin compound, tool-use rate, correct-after-tool, misinterpretation count, stratum floor (all blocking); enriched-vs-non reporting (informational). Admits a ceiling-saturated bucket so trivial wins do not dilute harder strata.

Reproducible in under a minute

pnpm install, run the checksum verifier, run the release-gate CLI against the canonical baseline. .gitattributes pins LF for sha256 + dataset tree so it works on Windows native, macOS, Linux, and WSL.

Slice 22 baseline PASSES

The revised gate (axes 2 + 6 with ceiling_saturated_pass) admits the canonical baseline cleanly. The Slice 19 baseline still FAILS — kept as a regression diagnostic so the gate has teeth.

Cited and licensed end-to-end

CITATION.cff, Zenodo deposition metadata (13 fields, ISO 639-3 language code), CC-BY-SA-3.0-DE preserved across the MIDI arrangements (Krueger) and the annotations + traces + evals (mcp-tool-shop-org).

Honest about provenance

Two songs in the source corpus (Satie, Debussy) are NOT in the public subset because their piano-midi.de provenance could not be verified during URL audit. Excluded rather than included on faith.

Verify the package

git clone https://github.com/mcp-tool-shop-org/ai-jam-sessions.git
cd ai-jam-sessions && pnpm install

# 273 checksum entries; ~2 seconds.
pnpm exec tsx scripts/verify-public-package-checksums.ts

Reproduce the canonical PASS

pnpm exec tsx scripts/check-release-gate.ts \
  datasets/jam-actions-v0-public/evals/\
slice21-fair-e3-baseline-results.json
# → "Verdict: PASS"

Read the dataset card

# Full HF-format dataset card + YAML frontmatter
open datasets/jam-actions-v0-public/README.md

# Zenodo deposition metadata (13 fields)
cat datasets/jam-actions-v0-public/zenodo-metadata.json

Cite it

# Citation File Format (CFF)
cat datasets/jam-actions-v0-public/CITATION.cff

# Bernd Krueger (piano-midi.de) for the MIDI arrangements.
# mcp-tool-shop-org for the annotations, traces, and evals.
# Both under CC-BY-SA-3.0-DE.

Install globally

npm install -g @mcptoolshop/ai-jam-sessions

Claude Desktop config

{
  "mcpServers": {
    "ai_jam_sessions": {
      "command": "npx",
      "args": [
        "-y", "-p",
        "ai-jam-sessions",
        "ai-jam-sessions-mcp"
      ]
    }
  }
}

Play a song

# Play Fur Elise at 70% speed
ai-jam-sessions play fur-elise --speed 0.7

# View piano roll as SVG
ai-jam-sessions view autumn-leaves --measures 1-16

# Sing along with piano
ai-jam-sessions sing imagine --with-piano

Guitar tablature

# View interactive guitar tab
ai-jam-sessions view-guitar greensleeves

# List tunings and voices
ai-jam-sessions list --genre folk