# Singing Pitch Tracker (pypi · pitch-mcp)

Real-time pitch detection and score alignment for a singer, from microphone input

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-01

## Components

- pypi · `pitch-mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/raulkivi-pitch-mcp/pitch-mcp.md), [page](https://verifymcp.io/servers/raulkivi-pitch-mcp/pitch-mcp)

## Channel facts

- Registry: `pypi`
- Package: `pitch-mcp`
- Version: `0.3.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-01.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 4 of 68 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to raulkivi/sheet-music-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 386 tokens (~55/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Singing Pitch Tracker MCP server?

Singing Pitch Tracker runs locally as a PyPI package, launched with uvx pitch-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add raulkivi-pitch-mcp -- uvx pitch-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "raulkivi-pitch-mcp": {
      "command": "uvx",
      "args": [
        "pitch-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "raulkivi-pitch-mcp": {
      "command": "uvx",
      "args": [
        "pitch-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add raulkivi-pitch-mcp -- uvx pitch-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "raulkivi-pitch-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "pitch-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add raulkivi-pitch-mcp --command uvx --arg pitch-mcp
```

### Hermes

```yaml
mcp_servers:
  raulkivi-pitch-mcp:
    command: "uvx"
    args: ["pitch-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "raulkivi-pitch-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "pitch-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add raulkivi-pitch-mcp -t stdio -c uvx -a pitch-mcp
```

### Other

```json
{
  "mcpServers": {
    "raulkivi-pitch-mcp": {
      "command": "uvx",
      "args": [
        "pitch-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-01 (score 67, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-30 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-29 (score 67, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-28 (score 82, +25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 57, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-26 (score 72)

First indexed and scored.

## MCP tools (7)

### `analyze_recording` (~84 tokens)

Analyse a pre-recorded WAV file against a reference score. Returns per-note pitch accuracy and a summary histogram.

Input parameters:

- `audio_path` (string, required): Absolute path to a 16-bit PCM WAV file
- `musicxml` (string, required): MusicXML document as a string
- `part_id` (string, required): Part ID to compare against (e.g. 'Soprano')

### `load_score` (~64 tokens)

Load a reference MusicXML score into a named session. Returns a session_id to use with start_monitoring.

Input parameters:

- `musicxml` (string, required): MusicXML document as a string
- `part_id` (string, required): Part ID to monitor (e.g. 'Soprano')

### `start_monitoring` (~60 tokens)

Open the microphone and begin pitch detection against the loaded score. Requires a session_id from load_score.

Input parameters:

- `session_id` (string, required): Session ID from load_score
- `tempo_bpm` (integer): Override tempo in BPM (default: score tempo)

### `get_current_position` (~44 tokens)

Poll the current score position and pitch accuracy. Call repeatedly while monitoring. Returns measure, beat, and accuracy.

Input parameters:

- `session_id` (string, required): Session ID from load_score

### `stop_monitoring` (~40 tokens)

Stop the microphone and return a session summary. The session is cleaned up after this call.

Input parameters:

- `session_id` (string, required): Session ID from load_score

### `list_capabilities` (~22 tokens)

List supported formats, tools, and backend information for this server

### `health_check` (~72 tokens)

Check that all runtime dependencies are available and report their status. Use this to verify the server is set up correctly. Returns status for offline analysis (librosa/pYIN) and real-time monitoring (sounddevice/portaudio). Missing portaudio is a warning, not an error — offline analysis still works without it.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/raulkivi-pitch-mcp/pitch-mcp#diagnostics

## Score history

- 2026-10-01: 67
- 2026-09-30: 82
- 2026-09-29: 67
- 2026-09-28: 82
- 2026-09-27: 57
- 2026-09-26: 72

## Common questions

### What is the Singing Pitch Tracker MCP server?

Singing Pitch Tracker is an MCP server listed in the public MCP registry as io.github.raulkivi/pitch-mcp. Real-time pitch detection and score alignment for a singer, from microphone input. This page covers its PyPI package (pitch-mcp).

### Is the Singing Pitch Tracker MCP server safe to use?

Singing Pitch Tracker scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 1 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Singing Pitch Tracker MCP server expose?

Singing Pitch Tracker exposes 7 tools: analyze_recording, load_score, start_monitoring, get_current_position, stop_monitoring, and 2 more. Their descriptions and schemas cost roughly 386 tokens of context every time the server is loaded.

### Is the Singing Pitch Tracker MCP server still maintained?

Singing Pitch Tracker is still listed as active in the MCP registry. We last reached this channel on 1 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Singing Pitch Tracker MCP server under?

Singing Pitch Tracker declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/pitch-mcp/
- Socket report: https://socket.dev/pypi/package/pitch-mcp
- Repository: https://github.com/raulkivi/sheet-music-mcp
- Changelog RSS feed: https://verifymcp.io/servers/raulkivi-pitch-mcp/pitch-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/raulkivi-pitch-mcp/pitch-mcp.json
- HTML version of this page: https://verifymcp.io/servers/raulkivi-pitch-mcp/pitch-mcp