# txscribe (npm · @txscribe/mcp)

Transcribe a link, then read the transcript and summary from your txscribe account.

- Trust score: 69/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `txscribe.ai`: 38/100, [markdown](https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe.md), [page](https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe)
- npm · `@txscribe/mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe-mcp.md), [page](https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe-mcp)

## Channel facts

- Registry: `npm`
- Package: `@txscribe/mcp`
- Version: `0.2.0`
- 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 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 93 dependencies flagged as unhealthy.
- **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 10 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 779 tokens (~97/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 81% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 8 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 txscribe MCP server?

txscribe runs locally as an npm package, launched with npx -y @txscribe/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 ai-txscribe-txscribe -- npx -y @txscribe/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ai-txscribe-txscribe": {
      "command": "npx",
      "args": [
        "-y",
        "@txscribe/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-txscribe-txscribe": {
      "command": "npx",
      "args": [
        "-y",
        "@txscribe/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-txscribe-txscribe -- npx -y @txscribe/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-txscribe-txscribe": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@txscribe/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-txscribe-txscribe --command npx --arg -y --arg @txscribe/mcp
```

### Hermes

```yaml
mcp_servers:
  ai-txscribe-txscribe:
    command: "npx"
    args: ["-y", "@txscribe/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-txscribe-txscribe": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@txscribe/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-txscribe-txscribe -t stdio -c npx -a -y @txscribe/mcp
```

### Other

```json
{
  "mcpServers": {
    "ai-txscribe-txscribe": {
      "command": "npx",
      "args": [
        "-y",
        "@txscribe/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.

### 2026-11-05 (score 69, +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.

### 2026-11-02 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 65, +5)

- [security improvement] Source repository: fail → pass
- [functional regression] Security disclosure: unverified → fail

### 2026-10-27 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 59)

First indexed and scored.

## MCP tools (8)

### `list_transcriptions` (~73 tokens)

List transcriptions

The account's transcriptions, newest first. Pass the previous page's nextCursor to read on.

Input parameters:

- `cursor` (string): nextCursor from the previous page.
- `limit` (integer): Page size.
- `status` (string): The API's filter: all, active (still working), done, error.

### `transcribe_link` (~171 tokens)

Transcribe a link

Create a transcription from a link to a video or recording (YouTube, Google Drive, Dropbox and others; the recording is transcribed, never downloaded). Starts at once and uses the account's minutes. Returns the transcription with its id; poll get_transcription until status is done, then read get_transcript.

Input parameters:

- `captions` (boolean): YouTube only: use the video's own captions when they fit; uses no minutes.
- `diarization` (boolean): Label speakers (default true; not every language supports it).
- `language` (string): "auto", or one of the codes the API lists in openapi.json — a full tag such as en-US, pt-BR or es-MX, never "en". Omit for automatic detection.
- `url` (string, required): The link.

### `search_transcriptions` (~124 tokens)

Search transcriptions

Which of the account's recordings said something, and when. Looks for the words as one phrase in what was said (not in titles), in the newest 500 recordings (ones still processing or failed among them are skipped; truncated is true when there may be older ones, which are not read): give a distinctive word or short phrase, not a question. Each result has up to five matches with the second each starts at; read around one with get_transcript's from and to rather than reading the whole transcript.

Input parameters:

- `query` (string, required): The word or phrase.

### `get_transcription` (~39 tokens)

Transcription status

Status and metadata of one transcription: fetching, uploading, preparing, transcribing, done or error.

Input parameters:

- `id` (string, required): The transcription id.

### `get_transcript` (~225 tokens)

Read a transcript

The finished transcript. json gives segments with word timings and speakers (what the app shows); txt, srt and vtt give the file the app's Export menu makes. A long recording is a lot of text: pass from and to (seconds) for only the paragraphs around a moment, such as a match from search_transcriptions, or summaryOnly for the summary instead. Not ready yet answers with the not_ready error; check get_transcription first.

Input parameters:

- `format` (string): json, txt, srt or vtt.
- `from` (number): Seconds into the recording where the stretch to read starts. Paragraphs overlapping it come back whole.
- `id` (string, required)
- `speakers` (boolean): Include speaker names.
- `summaryOnly` (boolean): true: the summary instead of the transcript, as get_summary returns it. Leave format, from and to out with it: they are not used.
- `timestamps` (boolean): txt: include the time of each paragraph.
- `to` (number): Seconds into the recording where it ends.

### `get_summary` (~37 tokens)

Read a summary

The summary of a finished transcription and its status. Ask for one with request_summary if there is none yet.

Input parameters:

- `id` (string, required)

### `request_summary` (~78 tokens)

Request a summary

Ask for a summary of a finished transcription, or a new one. Returns at once with status generating; read it with get_summary.

Input parameters:

- `id` (string, required)
- `language` (string): Output language; defaults to the transcript's.
- `scene` (string): meeting, interview, lecture, … Omit to let the model choose.

### `delete_transcription` (~32 tokens)

Delete a transcription

Delete a transcription, its media and everything made from it. Cannot be undone.

Input parameters:

- `id` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe-mcp#diagnostics

## Score history

- 2026-11-05: 69
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 68
- 2026-11-01: 67
- 2026-10-31: 67
- 2026-10-30: 66
- 2026-10-29: 66
- 2026-10-28: 65
- 2026-10-27: 60
- 2026-10-26: 59
- 2026-10-25: 59

## Common questions

### What is the txscribe MCP server?

txscribe is an MCP server listed in the public MCP registry as ai.txscribe/txscribe. Transcribe a link, then read the transcript and summary from your txscribe account. This page covers its npm package (@txscribe/mcp).

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

txscribe scores 69 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. 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 txscribe MCP server expose?

txscribe exposes 8 tools: list_transcriptions, transcribe_link, search_transcriptions, get_transcription, get_transcript, and 3 more. Their descriptions and schemas cost roughly 779 tokens of context every time the server is loaded.

### Is the txscribe MCP server still maintained?

txscribe is still listed as active in the MCP registry. We last reached this channel on 5 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 txscribe MCP server under?

txscribe 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

- npm package: https://www.npmjs.com/package/@txscribe/mcp
- Socket report: https://socket.dev/npm/package/@txscribe/mcp
- Repository: https://github.com/txscribe-ai/txscribe-mcp
- Website: https://txscribe.ai/developers#mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-txscribe-txscribe/txscribe-mcp