# TranscriptLab (remote · api.transcriptlab.dev)

Turn YouTube videos and audio or video files into searchable, exportable transcripts.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-22

## Components

- remote · `api.transcriptlab.dev`: 69/100 (this document), [markdown](https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api.md), [page](https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api)

## Channel facts

- Endpoint: `https://api.transcriptlab.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-22.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, 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**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3222 tokens (~146/item across 22 items; 20 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 71% 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 20 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 22 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.
  - Supports UI / widget rendering.

## Install

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

TranscriptLab is a hosted endpoint at https://api.transcriptlab.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-transcriptlab-transcriptlab 'https://api.transcriptlab.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-transcriptlab-transcriptlab": {
      "url": "https://api.transcriptlab.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-transcriptlab-transcriptlab": {
      "type": "http",
      "url": "https://api.transcriptlab.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-transcriptlab-transcriptlab]
url = "https://api.transcriptlab.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-transcriptlab-transcriptlab": {
      "type": "remote",
      "url": "https://api.transcriptlab.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-transcriptlab-transcriptlab --url 'https://api.transcriptlab.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-transcriptlab-transcriptlab:
    url: "https://api.transcriptlab.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-transcriptlab-transcriptlab": {
      "Transport": "http",
      "Url": "https://api.transcriptlab.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-transcriptlab-transcriptlab -t streamable-http -u 'https://api.transcriptlab.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-transcriptlab-transcriptlab": {
      "type": "http",
      "url": "https://api.transcriptlab.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.

### 2026-11-22 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-21 (score 68, 0)

- [security] Resource “TranscriptLab launcher” now points somewhere else: ui://transcriptlab/launcher-v13 → ui://transcriptlab/launcher-v14
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “transcriptlab_get_transcript” rewrote its description, which is the text the model reads
- [security] Tool “transcriptlab_retrieve_transcript” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 124 → 146
- [functional improvement] Tool coverage: 65% → 71%
- [cosmetic] “transcriptlab_export_link” added an optional parameter “diarize”
- [cosmetic] “transcriptlab_export_link” added an optional parameter “engine”
- [cosmetic] “transcriptlab_export_link” added an optional parameter “tier”
- [cosmetic] “transcriptlab_get_transcript” added an optional parameter “diarize”
- [cosmetic] “transcriptlab_get_transcript” added an optional parameter “engine”
- [cosmetic] “transcriptlab_get_transcript” added an optional parameter “speakers”
- [cosmetic] “transcriptlab_get_transcript” added an optional parameter “tier”
- [cosmetic] “transcriptlab_retrieve_transcript” added an optional parameter “diarize”
- [cosmetic] “transcriptlab_retrieve_transcript” added an optional parameter “engine”
- [cosmetic] “transcriptlab_retrieve_transcript” added an optional parameter “speakers”
- [cosmetic] “transcriptlab_retrieve_transcript” added an optional parameter “tier”
- [cosmetic] “transcriptlab_search_transcript” added an optional parameter “diarize”
- [cosmetic] “transcriptlab_search_transcript” added an optional parameter “engine”
- [cosmetic] “transcriptlab_search_transcript” added an optional parameter “tier”
- [cosmetic] “transcriptlab_get_transcript” reworded the description of “cleanup”

### 2026-11-20 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “transcriptlab_get_usage” rewrote its description, which is the text the model reads
- [functional] New tool “transcriptlab_create_checkout_link”

### 2026-11-19 (score 68, +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.

### 2026-11-18 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-17 (score 67)

First indexed and scored.

## MCP tools (20)

### `transcriptlab_get_transcript` (~457 tokens)

Get YouTube transcript

Get a YouTube transcript. Use when the user gives a YouTube link or video ID and wants the transcript. Default engine=captions reads existing YouTube captions; engine=stt is opt-in speech-to-text (slower, billed per audio minute — 1 credit/min standard, 10 credits/min with speaker labels). Never switch to engine=stt silently: only pass engine=stt when the user explicitly opts in or asks to transcribe the audio. Returns the transcript, or a job id when the request outlives the synchronous window: if a job comes back, poll transcriptlab_get_job_status, then read the text with transcriptlab_retrieve_transcript. The first delivery of each transcript variant can spend credits; later deliveries of that variant are free. When the source is an attached file or a direct media link, use transcriptlab_transcribe_file or transcriptlab_transcribe_media_url.

Input parameters:

- `also` (array): Additional formats to include in a JSON response.
- `cleanup` (boolean): Strip filler words and stray timestamps from the transcript text.
- `diarize` (boolean): Label speakers in the transcript. Requires engine=stt; implies tier=premium.
- `engine` (string): captions (default) reads YouTube caption tracks; stt transcribes the audio (opt-in only, billed per audio minute).
- `format` (string): Output format; defaults to json.
- `lang` (string): Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language.
- `metadata` (boolean): Include video metadata when available; defaults to true.
- `speakers` (string): Rename diarization labels for engine=stt, e.g. "Speaker 1=Host,Speaker 2=Guest".
- `tier` (string): Speech model tier for engine=stt; normal bills 1 credit/min, premium bills 10 credits/min and supports speaker labels. Defaults to auto.
- `translate` (string): Translate captions to this language when available.
- `type` (string): Caption track type; defaults to any.
- `url` (string, required): YouTube video URL or 11-character video ID.

### `transcriptlab_retrieve_transcript` (~285 tokens)

Retrieve completed transcript

Read a YouTube transcript that is already published for this account, without starting a new fetch. Use it after transcriptlab_get_job_status reports a job done, or to re-open a variant that was delivered before. For a first request use transcriptlab_get_transcript instead. Pass the same engine/tier/diarize used for the original fetch so the read selects the matching artifact. Reading an already delivered variant is free; a never-before-delivered variant can spend credits like the original request.

Input parameters:

- `cleanup` (boolean)
- `diarize` (boolean): Must match the original fetch; implies tier=premium for engine=stt.
- `engine` (string): Selects the captions or speech-to-text artifact; must match the original fetch.
- `format` (string)
- `lang` (string): Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language.
- `metadata` (boolean)
- `speakers` (string): Speaker label renames; must match the original fetch.
- `tier` (string): Speech tier for engine=stt; must match the original fetch.
- `translate` (string): Translation target, if requested for the original fetch.
- `type` (string)
- `url` (string, required): YouTube video URL or 11-character video ID.

### `transcriptlab_discover_captions` (~90 tokens)

Discover caption tracks

List the caption languages and track types (manual vs generated) available for a YouTube video. Use when the user asks which languages or subtitles a video has, or before transcriptlab_get_transcript when they want a specific language. Free in transcript credits, but subject to the account monthly discovery limit.

Input parameters:

- `url` (string, required): YouTube video URL or 11-character video ID.

### `transcriptlab_search_transcript` (~322 tokens)

Search a cached transcript

Search, quote, or slice a transcript already delivered to this account. Use for "find the part where...", keyword or regex lookup, or paginating a long transcript into chunks. It never starts a fetch and never charges transcript credits, so it only works on a video already cached here: deliver it first with transcriptlab_get_transcript if it is not. mode chooses the behavior: keyword matches terms, regex matches a pattern, chunk returns sequential sections.

Input parameters:

- `case_sensitive` (boolean)
- `context_chars` (integer)
- `diarize` (boolean): Must match the original fetch; requires engine=stt.
- `engine` (string): Search the captions artifact by default; engine=stt searches the speech-to-text transcript instead — use it when the video was transcribed with engine=stt.
- `flags` (string): Optional regular expression flags.
- `lang` (string)
- `max_tokens` (integer)
- `mode` (string, required): keyword matches terms, regex matches pattern, chunk returns sequential sections.
- `overlap_snippets` (integer)
- `pattern` (string): Required in regex mode.
- `target_tokens` (integer)
- `terms` (array): Required in keyword mode.
- `tier` (string): Speech tier for engine=stt; must match the tier the transcript was fetched with (auto resolves to whichever artifact exists).
- `translate` (string)
- `type` (string)
- `url` (string, required): YouTube video URL or 11-character video ID.

### `transcriptlab_get_job_status` (~85 tokens)

Check transcript job

Check whether a transcript job from transcriptlab_get_transcript has finished. Use it when that tool returned a job_id instead of a transcript. Returns status only, delivers no transcript, and spends no credits; once it reports done, read the text with transcriptlab_retrieve_transcript.

Input parameters:

- `job_id` (string, required): Job id returned by transcriptlab_get_transcript.

### `transcriptlab_get_usage` (~48 tokens)

Check TranscriptLab usage

Read the account plan, remaining credits, and current-period usage, plus upgrade options. Use when the user asks about cost, balance, or limits, or before a credit-spending request.

### `transcriptlab_create_checkout_link` (~144 tokens)

Create a checkout link to add credits

Create a hosted Dodo checkout link bound to the user's connected TranscriptLab account (no website sign-in required). Use when the user runs out of credits (insufficient_credits), asks to upgrade, or wants to buy more credits. Choose starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits). Always show the returned checkout_url verbatim as a clickable link.

Input parameters:

- `offer` (string, required): starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits).

### `transcriptlab_list_transcripts` (~101 tokens)

List transcript library

List YouTube videos whose transcripts were already delivered to this account, most recent first. Use it to find or reopen an earlier transcript. It fetches nothing and delivers no transcript. When more results exist, page with the returned cursor.

Input parameters:

- `cursor` (string): Opaque cursor returned by the previous page.
- `limit` (integer): Page size; defaults to the server default.
- `search` (string): Optional video ID or title filter.

### `transcriptlab_mentions` (~70 tokens)

Transcript library

Composer at-mention search over the account’s transcript library, used to build the @TranscriptLab picker. App-facing only: the host calls it, it returns resource links rather than transcript text, and the model should not call it.

Input parameters:

- `query` (string): Typeahead text; may be empty.

### `transcriptlab_open_audio` (~101 tokens)

Transcribe an audio file

Entry point the host invokes when the user opens an audio or video file with this plugin: opens the uploader view and starts speech-to-text. You do not call this directly; for a file attached to the conversation use transcriptlab_transcribe_file.

Input parameters:

- `diarize` (boolean): Label speakers; defaults to false. Implies tier=premium and 10 credits per audio minute.
- `file` (object, required): Host-provided handle for the opened file.

### `transcriptlab_begin_audio_upload` (~62 tokens)

Begin audio upload

Create a signed direct-upload session for an opened audio file. App-facing only: the uploader view calls it, not the model.

Input parameters:

- `bytes` (integer, required)
- `content_type` (string, required): Media MIME type.
- `name` (string, required)

### `transcriptlab_start_audio_transcription` (~93 tokens)

Transcribe uploaded audio

Finalize a signed upload and start speech-to-text on it. App-facing only: the uploader view calls it once the file is uploaded. Spends credits per audio minute.

Input parameters:

- `diarize` (boolean): Label speakers; defaults to false. Implies tier=premium.
- `tier` (string): Speech model tier; defaults to auto (normal when available).
- `upload_id` (string, required)

### `transcriptlab_read_audio_transcript` (~53 tokens)

Read uploaded-audio transcript

Read the transcript of a file uploaded through the uploader view. A pending transcription reports 202; retry shortly. App-facing only.

Input parameters:

- `format` (string)
- `upload_id` (string, required)

### `transcriptlab_open` (~141 tokens)

Open TranscriptLab

Open the TranscriptLab launcher view, where the user can work with transcripts visually and send one into the chat with "Discuss in chat". Use tab "upload" when a file needs the uploader: the user wants to pick a local audio or video file, the attached file is too large or could not be read by transcriptlab_transcribe_file, or that upload failed. Use "library" to reopen earlier transcripts, and "link" (the default) to paste a YouTube link. Also offer it when the user wants a transcript but has given no link or file.

Input parameters:

- `tab` (string): Which launcher tab to show first; defaults to link.

### `transcriptlab_transcribe_file` (~212 tokens)

Transcribe an attached audio or video file

Transcribe an audio or video file the user attached to this conversation, using speech-to-text (mp3, m4a, wav, mp4, webm and similar). Use it for an attached media file; YouTube links use transcriptlab_get_transcript instead. Spends credits per audio minute. Attachments up to 300 MB work here; larger files (up to 2 GB) use the launcher upload view. Stores the file, starts transcription, and returns an upload_id: poll transcriptlab_get_speech_transcript with it, waiting a few seconds between tries and stopping after about ten. Do not call this again for the same file. If it fails or the file is too large, call transcriptlab_open with tab "upload".

Input parameters:

- `diarize` (boolean): Label speakers; defaults to false. Implies tier=premium.
- `file` (object, required): The attached media file.
- `tier` (string): Speech model tier; defaults to auto (normal when available).

### `transcriptlab_transcribe_media_url` (~167 tokens)

Transcribe a direct media link

Transcribe a public https link to an audio or video file with speech-to-text. Use it for a direct media URL (ending in .mp3, .m4a, .wav, .mp4, .webm and similar); not for YouTube or other web pages, which use transcriptlab_get_transcript. Spends credits per audio minute. Returns a media_id: poll transcriptlab_get_speech_transcript with it, waiting a few seconds between tries and stopping after about ten.

Input parameters:

- `diarize` (boolean): Label speakers; defaults to false. Implies tier=premium.
- `tier` (string): Speech model tier; defaults to auto (normal when available).
- `url` (string, required): Public https URL of an audio or video file.

### `transcriptlab_get_speech_transcript` (~138 tokens)

Read a speech-to-text transcript

Read the speech-to-text transcript started by transcriptlab_transcribe_file (pass upload_id) or transcriptlab_transcribe_media_url (pass media_id). Pass exactly one id. While transcription runs it returns a pending result: wait a few seconds, back off, and stop after about ten tries; if it is still pending, tell the user the job is queued instead of looping. Reading does not start new work or add charges.

Input parameters:

- `format` (string): Defaults to json.
- `media_id` (string): From transcriptlab_transcribe_media_url.
- `upload_id` (string): From transcriptlab_transcribe_file.

### `transcriptlab_export_link` (~214 tokens)

Create a download link

Create a 10-minute signed download link (TXT, SRT, VTT, Markdown, or JSON) for a transcript the account already has, or for a transcribed upload. Call this when the user wants a file or a link to a file: hand them the returned url and say it expires in 10 minutes. Needs a signed-in connection. The launcher Download action calls it too, so a host that cannot start a download itself still gives the user the link.

Input parameters:

- `diarize` (boolean): Must match the original fetch; requires engine=stt.
- `engine` (string): Download the speech-to-text transcript for a video fetched with engine=stt.
- `format` (string)
- `lang` (string)
- `tier` (string): Speech tier for engine=stt; auto resolves to whichever artifact exists.
- `upload_id` (string): Upload id of a transcribed file.
- `url` (string): YouTube video URL or 11-character video ID.

### `transcriptlab_submit_batch` (~54 tokens)

Submit a batch transcript job

Queue a list of YouTube URLs as one batch job and return its job id. App-facing only. The plan caps how many URLs one job accepts.

Input parameters:

- `urls` (array, required): YouTube URLs to transcribe.

### `transcriptlab_list_job_items` (~54 tokens)

List job items

Return per-video results for a batch or channel job. App-facing only. Page with the returned cursor.

Input parameters:

- `cursor` (string)
- `job_id` (string, required)
- `limit` (integer)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api#diagnostics

## Score history

- 2026-11-22: 69
- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 68
- 2026-11-18: 67
- 2026-11-17: 67

## Common questions

### What is the TranscriptLab MCP server?

TranscriptLab is an MCP server listed in the public MCP registry as dev.transcriptlab/transcriptlab. Turn YouTube videos and audio or video files into searchable, exportable transcripts. This page covers its hosted endpoint (https://api.transcriptlab.dev/mcp).

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

TranscriptLab scores 69 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 TranscriptLab MCP server expose?

TranscriptLab exposes 20 tools: transcriptlab_get_transcript, transcriptlab_retrieve_transcript, transcriptlab_discover_captions, transcriptlab_search_transcript, transcriptlab_get_job_status, and 15 more. Their descriptions and schemas cost roughly 2,891 tokens of context every time the server is loaded.

### Does the TranscriptLab MCP server require authentication?

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

### Is the TranscriptLab MCP server still maintained?

TranscriptLab is still listed as active in the MCP registry. We last reached this channel on 22 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 TranscriptLab MCP server?

VerifyMCP ran 13 checks on TranscriptLab, covering TLS certificate, Authorization, HSTS header, DNSSEC and 9 more. One item could not be completed, a gap on our side rather than a finding about TranscriptLab: 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://api.transcriptlab.dev/mcp
- Repository: https://github.com/hussamsi2040/transcriptlab-claude-plugin
- Changelog RSS feed: https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api.json
- HTML version of this page: https://verifymcp.io/servers/dev-transcriptlab-transcriptlab/api
