# African Speech Corpora Quality Audit (pypi · african-speech-mcp)

Read-only, provenance-aware selection of Wolof speech corpora by measured quality.

- Trust score: 78/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `african-speech-mcp`: 78/100 (this document), [markdown](https://verifymcp.io/servers/papasega-african-speech-corpora/african-speech-mcp.md), [page](https://verifymcp.io/servers/papasega-african-speech-corpora/african-speech-mcp)

## Channel facts

- Registry: `pypi`
- Package: `african-speech-mcp`
- Version: `2.0.0`
- 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 2026-09-20.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 6 of 46 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (Apache Software License) isn't a recognized OSI-approved license.
  - Actively maintained (last published 23 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 555 tokens (~69/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 70% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 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).

## Install

### How do I install the African Speech Corpora Quality Audit MCP server?

African Speech Corpora Quality Audit runs locally as a PyPI package, launched with uvx african-speech-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 papasega-african-speech-corpora -- uvx african-speech-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "papasega-african-speech-corpora": {
      "command": "uvx",
      "args": [
        "african-speech-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "papasega-african-speech-corpora": {
      "command": "uvx",
      "args": [
        "african-speech-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add papasega-african-speech-corpora -- uvx african-speech-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add papasega-african-speech-corpora --command uvx --arg african-speech-mcp
```

### Hermes

```yaml
mcp_servers:
  papasega-african-speech-corpora:
    command: "uvx"
    args: ["african-speech-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "papasega-african-speech-corpora": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "african-speech-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add papasega-african-speech-corpora -t stdio -c uvx -a african-speech-mcp
```

### Other

```json
{
  "mcpServers": {
    "papasega-african-speech-corpora": {
      "command": "uvx",
      "args": [
        "african-speech-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.

### 2026-09-20 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (8)

### `list_corpora` (~50 tokens)

List language/task/config variants with audit and verification state.

Input parameters:

- `include_derivatives` (boolean): Include derivatives.
- `language`: ISO 639-3 filter.
- `task`: Task filter.

Output parameters:

- `audited_count` (integer)
- `corpora` (array)
- `derivatives_count` (integer)
- `disclaimer` (string)
- `originals_count` (integer)
- `queryable_count` (integer)
- `total` (integer)

### `search_segments` (~74 tokens)

Search a schema-verified variant. Config overrides cannot cross language boundaries; temporary audio URLs are explicitly marked ephemeral.

Input parameters:

- `config`: Compatibility parameter; must equal the variant config.
- `corpus` (string, required): Variant key.
- `limit` (integer)
- `query` (string, required)
- `split`: Declared split.

Output parameters:

- `filter_available` (boolean)
- `provenance`
- `query` (string)
- `returned` (integer)
- `segments` (array)
- `total_matches`
- `warnings` (array)

### `corpus_stats` (~28 tokens)

Return rows and schema for exactly one declared dataset configuration.

Input parameters:

- `corpus` (string, required): Variant key.

Output parameters:

- `columns` (array)
- `declared_splits` (array)
- `observed_configs` (array)
- `provenance`
- `splits` (array)
- `total_rows` (integer)
- `undeclared_splits` (array)
- `warnings` (array)

### `cite_corpus` (~28 tokens)

Return licence and citations, including parents of derivatives.

Input parameters:

- `corpus` (string, required): Variant key.

Output parameters:

- `also_cite` (array)
- `bibtex` (string)
- `commercial_use`
- `homepage` (string)
- `licence` (string)
- `usage_note` (string)

### `audit_corpus` (~58 tokens)

Return dated observed quality metrics separately from published figures. Missing observations remain null, never implicit zero.

Input parameters:

- `audit_id`: Specific audit snapshot.
- `corpus` (string, required): Variant key.
- `include_published` (boolean): Include source figures.

Output parameters:

- `audit_id`
- `audit_status` (string)
- `citation` (string)
- `commercial_use`
- `confidence`
- `config`
- `corpus` (string)
- `counts`
- `dataset_family` (string)
- `domain`
- `durations`
- `language` (string)
- `language_purity`
- `licence` (string)
- `measurement_method`
- `observed_at`
- `provenance`
- `published_metrics`
- `quality_notes`
- `source_reference`
- `speakers`
- `speech_type`
- `split_scope`
- `task` (string)
- `verification_basis`
- `warnings` (array)

### `plan_training_set` (~137 tokens)

Build a de-duplicated variant plan using published or dated audit metrics, with explicit quality, licence, benchmark and language-purity decisions.

Input parameters:

- `exclude_evaluation_sets`: Deprecated compatibility alias for include_benchmarks.
- `include_benchmarks` (boolean): Include evaluation benchmarks.
- `include_mixed_language` (boolean): Opt in to known mixed-language variants.
- `include_tts_for_asr` (boolean): Explicitly permit TTS variants in an ASR plan.
- `language` (string)
- `metric_source`: Metric provenance.
- `quality`: Minimum/selection quality.
- `task`: Requested task.

Output parameters:

- `assumed_valid_duration`
- `citations` (array)
- `excluded_derivatives` (array)
- `excluded_variants` (object)
- `expert_verified_duration`
- `hours_unknown_for` (array)
- `include_benchmarks` (boolean)
- `include_mixed_language` (boolean)
- `include_tts_for_asr` (boolean)
- `included` (array)
- `language` (string)
- `licences` (array)
- `metric_source` (string)
- `quality` (string)
- `task` (string)
- `total_duration`
- `total_hours_transcribed` (number): Compatibility alias for total_duration.hours_decimal.
- `warnings` (array)

### `filter_segments` (~96 tokens)

Filter rows only when a versioned row-level audit manifest exists; aggregated audit totals alone produce a structured refusal.

Input parameters:

- `corpus` (string, required): Variant key.
- `exclude_corrupt` (boolean)
- `exclude_duplicates` (boolean)
- `exclude_non_wolof` (boolean)
- `limit` (integer)
- `min_quality`: Requested row quality.
- `query`
- `split`: Declared split.

Output parameters:

- `audit_id`
- `corpus` (string)
- `filter_available` (boolean)
- `manifest_path`
- `provenance`
- `reason` (string)
- `required_manifest_columns` (array)
- `segments` (array)
- `warnings` (array)

### `compare_corpora` (~29 tokens)

Compare variant quality, provenance, licence and benchmark status.

Input parameters:

- `corpora` (array, required)

Output parameters:

- `compared` (integer)
- `corpora` (array)
- `warnings` (array)

## Diagnostics

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

## Score history

- 2026-09-20: 78
- 2026-09-19: 77
- 2026-09-18: 77
- 2026-09-17: 76
- 2026-09-16: 76
- 2026-09-15: 75
- 2026-09-14: 75
- 2026-09-13: 74
- 2026-09-12: 74
- 2026-09-11: 73
- 2026-09-10: 73
- 2026-09-09: 72
- 2026-09-08: 72
- 2026-09-07: 72
- 2026-09-06: 71
- 2026-09-05: 71
- 2026-09-04: 70
- 2026-09-03: 66
- 2026-09-02: 66
- 2026-09-01: 66
- 2026-08-31: 66
- 2026-08-30: 66
- 2026-08-29: 66
- 2026-08-28: 66
- 2026-08-27: 51

## Common questions

### What is the African Speech Corpora Quality Audit MCP server?

African Speech Corpora Quality Audit is an MCP server listed in the public MCP registry as io.github.papasega/african-speech-corpora. Read-only, provenance-aware selection of Wolof speech corpora by measured quality. This page covers its PyPI package (african-speech-mcp).

### Is the African Speech Corpora Quality Audit MCP server safe to use?

African Speech Corpora Quality Audit scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 African Speech Corpora Quality Audit MCP server expose?

African Speech Corpora Quality Audit exposes 8 tools: list_corpora, search_segments, corpus_stats, cite_corpus, audit_corpus, and 3 more. Their descriptions and schemas cost roughly 500 tokens of context every time the server is loaded.

### Is the African Speech Corpora Quality Audit MCP server still maintained?

African Speech Corpora Quality Audit is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

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