# AudioWrench Audio Tools (remote · audiowrench-mcp.tarsanbeats.workers.dev)

Reverse or trim selected WAV files, or transcribe WAV to TXT/SRT with Whisper Tiny and Base.

- Trust score: 56/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `audiowrench-mcp.tarsanbeats.workers.dev`: 56/100 (this document), [markdown](https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp.md), [page](https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp)

## Channel facts

- Endpoint: `https://audiowrench-mcp.tarsanbeats.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0-beta.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (aw.session.close).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 403, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2793 tokens (~121/item across 23 items; 23 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 34% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "aw.transfer.guide" implies "transfer" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 24 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 AudioWrench Audio Tools MCP server?

AudioWrench Audio Tools is a hosted endpoint at https://audiowrench-mcp.tarsanbeats.workers.dev/mcp, so there is nothing to install locally. 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 --transport http dev-workers-tarsanbeats-audiowrench-mcp-audio-to 'https://audiowrench-mcp.tarsanbeats.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-workers-tarsanbeats-audiowrench-mcp-audio-to": {
      "url": "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-workers-tarsanbeats-audiowrench-mcp-audio-to": {
      "type": "http",
      "url": "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-workers-tarsanbeats-audiowrench-mcp-audio-to]
url = "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-workers-tarsanbeats-audiowrench-mcp-audio-to": {
      "type": "remote",
      "url": "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-workers-tarsanbeats-audiowrench-mcp-audio-to --url 'https://audiowrench-mcp.tarsanbeats.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-workers-tarsanbeats-audiowrench-mcp-audio-to:
    url: "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-workers-tarsanbeats-audiowrench-mcp-audio-to": {
      "Transport": "http",
      "Url": "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-workers-tarsanbeats-audiowrench-mcp-audio-to -t streamable-http -u 'https://audiowrench-mcp.tarsanbeats.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-workers-tarsanbeats-audiowrench-mcp-audio-to": {
      "type": "http",
      "url": "https://audiowrench-mcp.tarsanbeats.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-20 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 55, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-17 (score 54)

First indexed and scored.

## MCP tools (23)

### `aw.status` (~16 tokens)

Read public beta coverage and service limits.

### `aw.catalog` (~37 tokens)

Find supported public beta workflows by task.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `query` (string)

### `aw.session.open` (~31 tokens)

Create a private15-minute remote processing session. No local installation and no personal input is sent by opening it.

### `aw.session.close` (~52 tokens)

Explicitly revoke this transient remote session and remove its remote copies; original disk files are never touched.

Input parameters:

- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.jobs.list` (~46 tokens)

Statuses for this session only, without selected audio or private URLs.

Input parameters:

- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.jobs.cancel` (~81 tokens)

Retire active work AND in-flight uploads that have not committed. Completed immutable inputs/artifacts are not deleted. Stable upload UUID/operationId reconcile committed receipts. Bounded32 cancellation requests remain available after ordinary quota exhaustion; close clears active copies.

Input parameters:

- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.artifact.verify` (~60 tokens)

Re-read authenticated chunks and hash an actual current-session artifact; return metadata, never audio bytes.

Input parameters:

- `artifactId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.transfer.guide` (~30 tokens)

Explicit native MCP file-transfer contract, bounds and client-history privacy. Discovery does not read your disk.

### `aw.input.begin` (~98 tokens)

Reserve bounded encrypted staging for one explicitly selected file. NO source publication or job retirement until validated commit;2 pending/max24 identities.

Input parameters:

- `format` (string, required)
- `inputId` (string, required)
- `selectedByUser` (boolean, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `sha256` (string, required)
- `totalBytes` (integer, required)

### `aw.input.write_chunk` (~95 tokens)

Append one exact canonical-base6432768-byte chunk (last=remainder) to this attempt in order. Exact retries reconcile; binary bodies may reach client/model history.

Input parameters:

- `attempt` (string, required)
- `data` (string, required)
- `inputId` (string, required)
- `offset` (integer, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.input.status` (~66 tokens)

Resume this exact transfer attempt without returning any selected bytes. Retired/complete state is explicit.

Input parameters:

- `attempt` (string, required)
- `inputId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.input.commit` (~81 tokens)

Verify ALL staged bytes/hash/original format and atomically publish one current immutable input. Exact completed retries recover its receipt; invalid/partial data never retires a job.

Input parameters:

- `attempt` (string, required)
- `inputId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.input.abort` (~77 tokens)

Discard this pending transfer attempt only; does not cancel the current processing job or delete a completed immutable input. Use jobs.cancel for all pending stages.

Input parameters:

- `attempt` (string, required)
- `inputId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.artifact.read_chunk` (~92 tokens)

Return one bounded binary embedded resource from this session artifact, plus range/whole-file hashes. Reassemble and hash ALL bytes. Not disk-save or whole-file verification from one range.

Input parameters:

- `artifactId` (string, required)
- `length` (integer)
- `offset` (integer, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.

### `aw.speech.whisper_encode_step` (~240 tokens)

Prepare the exact original Tiny or Base encoder in separate bounded calls: two for Tiny, three for Base. Begin with the accepted WAV source and no continuation. While status is encoder-pending, supply its opaque continuation with the same session, source and model and a new operationId. Retry the same operationId with identical arguments only; no automatic model retry. After encoder-prepared, choose decoderRoutes.fileOnly for a whole file without replacing the current transcript, or decoderRoutes.currentTranscript for a whole file plus shared current segments, export and Clear. Both use the same prepared handle, session, source and model; start with null decoder continuation. Never switch tools with a pending decoder continuation. Intermediate activations stay in the encrypted session; no upload, download or transcript is produced by this tool.

Input parameters:

- `continuation` (string)
- `model` (string)
- `operationId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `source` (string, required): An immutable input or result handle belonging to this session; never a URL/path/base64.

### `aw.speech.whisper_decode_step` (~341 tokens)

Explicit bounded continuation of the REAL original Tiny/Base decoder for a whole accepted selected WAV. First call uses the SAME-session original encoder handle and null continuation. A nonterminal step returns only an opaque encrypted SAME-session decoder-pending handle, NOT a transcript; call this tool explicitly again with identical source/prepared/model/language/output, the CURRENT returned handle and a new operationId. Original complete token history, logits/stopping rules and full TXT/SRT remain unchanged; each call yields after at most64 original nonterminal steps for Tiny or32 for Base and keeps the existing30s work limit, session caps, TTL/admission and quotas. Rebuilds constant encoder KV with one original initial decoder forward and verifies retained exact hashes. Base reprojects six original values from the same pinned encoder source as needed; no new encoder run. Atomically replaces old private state; cancel/failure preserves the last accepted state. Consumed pending handles fail SUPERSEDED, not automatic heavy retry. No cache upload/download/inline tensors, model change, truncation, native CPU preemption, accuracy/all139/physical capacity/client disk access or provider acceptance claim. Auto retains original English default; original padded timestamps require review.

Input parameters:

- `continuation`
- `language` (string)
- `model` (string)
- `operationId` (string, required)
- `output` (string)
- `prepared` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `source` (string, required): An immutable input or result handle belonging to this session; never a URL/path/base64.

### `aw.speech.transcribe` (~289 tokens)

Original Tiny/Base whole-file transcription with a CURRENT shared transcript. Explicit SAME-session original encoder handle required; Run at most64 original decoder steps for Tiny or32 for Base per explicit call, with identical source/model/language/output and the CURRENT handle returned by this same tool. Use a NEW operationId only when advancing; after a failed call reconcile jobs and the last accepted receipt before deciding whether to explicitly resubmit the exact same UUID and inputs. Never swap in the file-only decoder continuation. Pending is NOT text. On original completion atomically retain validated original segments in this session encrypted vault and return a whole TXT/SRT plus transcript handle. Read segments or export BOTH original formats without another inference; Clear is separate. Old whisper file tools unchanged. Same30s/TTL/storage/jobs/admission/quotas, no truncation, automatic heavy retry, device/OS recognition, E2EE/backup erasure/all139/capacity/accuracy claim.

Input parameters:

- `continuation`
- `language` (string)
- `model` (string)
- `operationId` (string, required)
- `output` (string)
- `prepared` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `source` (string, required): An immutable input or result handle belonging to this session; never a URL/path/base64.

### `aw.speech.transcript.read` (~134 tokens)

Read CURRENT accepted original transcript segments and exact time values, explicitly, in bounded pages. Null transcript selects current state; an expected handle fences stale/cleared/newer results. No model I/O, recording or unfinished text. Remote selected transcript text is returned only by this explicit read. Empty state is useful; no editing or calibrated alignment claim. Same session/source epoch/engine/expiry/privacy bounds.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `transcript`

### `aw.speech.transcript.export` (~145 tokens)

Export the CURRENT accepted transcript as exact original TXT or SRT, with NO model call. Same original serializers/timestamp fallback/CRLF, verified immutable header-auth artifact. Explicit current handle and UUID; replay requires same current generation/source/settings and actual verified bytes. Nothing to export after Clear/empty; stale/current-source mismatch rejects. A previously downloaded export is not erased by Clear. No browser OS-save/accuracy/backup-erasure claim.

Input parameters:

- `operationId` (string, required)
- `output` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `transcript` (string, required)

### `aw.speech.transcript.clear` (~152 tokens)

Explicitly clear the EXPECTED CURRENT shared transcript only and leave an empty generation, matching original Clear semantics. Null succeeds only when no current state exists; a stale handle cannot clear a newer result. Does NOT cancel in-flight transcription, selected input, encoder/pending state, or previously downloaded immutable exports. A later valid model completion may populate the transcript again. Exact UUID replay must still refer to the same cleared generation. Removes active private encrypted snapshot, NOT irreversible provider backups/E2EE; no new model/device I/O.

Input parameters:

- `operationId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `transcript` (required)

### `aw.speech.whisper_export_txt` (~154 tokens)

Export the original TXT from a complete current-session SRT produced by aw.speech.whisper_decode_step, without invoking the model again. Only a verified original decoder SRT artifact in the same active source revision is accepted; no imported SRT, other session, stale source, or unfinished state. Keeps the original whole-second timestamps, text and CRLF. Returns a verified immutable authenticated TXT artifact, not inline transcript content. Reuse operationId for the same SRT; inspect the job before an explicit retry.

Input parameters:

- `operationId` (string, required)
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `srt` (string, required)

### `aw.audio.reverse` (~103 tokens)

Reverse every channel with the actual AudioWrench core; verified new PCM WAV.

Input parameters:

- `float32` (boolean)
- `operationId` (string, required): Stable operation UUID for safe retry/reconciliation; reuse only with identical sources/settings.
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `source` (string, required): An immutable input or result handle belonging to this session; never a URL/path/base64.

### `aw.audio.trim` (~118 tokens)

Copy the current source-frame interval using the unchanged core floor-to-frame semantics.

Input parameters:

- `endSeconds` (number, required)
- `float32` (boolean)
- `operationId` (string, required): Stable operation UUID for safe retry/reconciliation; reuse only with identical sources/settings.
- `session` (string, required): Private short-lived session capability returned by aw.session.open. Never publish or log it.
- `source` (string, required): An immutable input or result handle belonging to this session; never a URL/path/base64.
- `startSeconds` (number, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp#diagnostics

## Score history

- 2026-11-21: 56
- 2026-11-20: 56
- 2026-11-19: 55
- 2026-11-18: 55
- 2026-11-17: 54

## Common questions

### What is the AudioWrench Audio Tools MCP server?

AudioWrench Audio Tools is an MCP server listed in the public MCP registry as dev.workers.tarsanbeats.audiowrench-mcp/audio-tools. Reverse or trim selected WAV files, or transcribe WAV to TXT/SRT with Whisper Tiny and Base. This page covers its hosted endpoint (https://audiowrench-mcp.tarsanbeats.workers.dev/mcp).

### Is the AudioWrench Audio Tools MCP server safe to use?

AudioWrench Audio Tools scores 56 out of 100 on VerifyMCP. 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 AudioWrench Audio Tools MCP server expose?

AudioWrench Audio Tools exposes 23 tools: aw.status, aw.catalog, aw.session.open, aw.session.close, aw.jobs.list, and 18 more. Their descriptions and schemas cost roughly 2,538 tokens of context every time the server is loaded.

### Does the AudioWrench Audio Tools MCP server require authentication?

No. We connected to AudioWrench Audio Tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AudioWrench Audio Tools MCP server still maintained?

AudioWrench Audio Tools 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 did VerifyMCP test on the AudioWrench Audio Tools MCP server?

VerifyMCP ran 12 checks on AudioWrench Audio Tools, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about AudioWrench Audio Tools: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://audiowrench-mcp.tarsanbeats.workers.dev/mcp
- Website: https://audiowrench.com/
- Changelog RSS feed: https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-workers-tarsanbeats-audiowrench-mcp-audio-tools/audiowrench-mcp
