# Parlova (pypi · parlova)

Transcribe local audio/video and YouTube into timestamped, speaker-labelled text. 90+ languages.

- Trust score: 58/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `parlova`: 58/100 (this document), [markdown](https://verifymcp.io/servers/fort652-parlova-mcp/parlova.md), [page](https://verifymcp.io/servers/fort652-parlova-mcp/parlova)

## Channel facts

- Registry: `pypi`
- Package: `parlova`
- Version: `1.0.1`
- 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 2026-11-21.

- **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.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 358 tokens (~71/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Parlova MCP server?

Parlova runs locally as a PyPI package, launched with uvx parlova 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 fort652-parlova-mcp -- uvx parlova mcp
```

### Cursor

```json
{
  "mcpServers": {
    "fort652-parlova-mcp": {
      "command": "uvx",
      "args": [
        "parlova",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fort652-parlova-mcp": {
      "command": "uvx",
      "args": [
        "parlova",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add fort652-parlova-mcp -- uvx parlova mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fort652-parlova-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "parlova",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fort652-parlova-mcp --command uvx --arg parlova --arg mcp
```

### Hermes

```yaml
mcp_servers:
  fort652-parlova-mcp:
    command: "uvx"
    args: ["parlova", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "fort652-parlova-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "parlova",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add fort652-parlova-mcp -t stdio -c uvx -a parlova mcp
```

### Other

```json
{
  "mcpServers": {
    "fort652-parlova-mcp": {
      "command": "uvx",
      "args": [
        "parlova",
        "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.

### 2026-11-21 (score 58, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-20 (score 73, +4)

- [functional improvement] Stability: unverified → 0.30

### 2026-11-18 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-17 (score 54, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-15 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-14 (score 54, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-12 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-11 (score 54)

First indexed and scored.

## MCP tools (5)

### `transcribe_file` (~129 tokens)

Transcribe an audio or video file on this computer with Parlova and return the text. Waits for the result (up to max_wait_seconds); if it isn't ready by then, returns the job id to check later with get_transcript.

Input parameters:

- `language` (string): Spoken language code such as 'en', or 'auto' (default).
- `max_wait_seconds` (integer): How long to wait for the result (default 240).
- `path` (string, required): Absolute path to the audio or video file.
- `speakers` (boolean): Label who said what (Plus/Pro).

### `transcribe_youtube` (~93 tokens)

Transcribe a YouTube video by its link and return the text. Waits like transcribe_file.

Input parameters:

- `language` (string): Spoken language code, or 'auto' (default).
- `max_wait_seconds` (integer): How long to wait for the result (default 240).
- `speakers` (boolean): Label who said what (Plus/Pro).
- `url` (string, required): YouTube link.

### `get_transcript` (~60 tokens)

Get a transcript by job id: readable text with timestamps and speakers, or a file format (srt, vtt, csv, md, json, txt).

Input parameters:

- `format` (string): Default: text.
- `job_id` (string, required)

### `list_transcripts` (~35 tokens)

List recent Parlova transcriptions with their ids, status, dates and titles.

Input parameters:

- `limit` (integer): Default 20.

### `get_usage` (~25 tokens)

Minutes of transcription used this month, the plan's limit, and recent monthly totals.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/fort652-parlova-mcp/parlova#diagnostics

## Score history

- 2026-11-21: 58
- 2026-11-20: 73
- 2026-11-19: 69
- 2026-11-18: 69
- 2026-11-17: 54
- 2026-11-16: 69
- 2026-11-15: 69
- 2026-11-14: 54
- 2026-11-13: 69
- 2026-11-12: 69
- 2026-11-11: 54

## Common questions

### What is the Parlova MCP server?

Parlova is an MCP server listed in the public MCP registry as io.github.fort652/parlova-mcp. Transcribe local audio/video and YouTube into timestamped, speaker-labelled text. 90+ languages. This page covers its PyPI package (parlova).

### Is the Parlova MCP server safe to use?

Parlova scores 58 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 Parlova MCP server expose?

Parlova exposes 5 tools: transcribe_file, transcribe_youtube, get_transcript, list_transcripts, get_usage. Their descriptions and schemas cost roughly 342 tokens of context every time the server is loaded.

### Is the Parlova MCP server still maintained?

Parlova is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Parlova MCP server under?

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

### What did VerifyMCP test on the Parlova MCP server?

VerifyMCP ran 15 checks on Parlova, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Parlova: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/parlova/
- Socket report: https://socket.dev/pypi/package/parlova
- Repository: https://github.com/fort652/parlova-mcp
- Website: https://parlova.co.za/
- Changelog RSS feed: https://verifymcp.io/servers/fort652-parlova-mcp/parlova.xml
- Changelog JSON feed: https://verifymcp.io/servers/fort652-parlova-mcp/parlova/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/fort652-parlova-mcp/parlova.json
- HTML version of this page: https://verifymcp.io/servers/fort652-parlova-mcp/parlova
