# Caption Checker (mcpb · caption-checker-1.3.3.mcpb)

Check, fix, convert and retime SRT and WebVTT captions against Netflix, BBC and DCMP limits.

- Trust score: 50/100 (low)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `caption-checker-1.3.3.mcpb`: 50/100 (this document), [markdown](https://verifymcp.io/servers/markksantos-caption-checker/caption-checker.md), [page](https://verifymcp.io/servers/markksantos-caption-checker/caption-checker)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/markksantos/caption-checker/releases/download/v1.3.3/caption-checker-1.3.3.mcpb`
- Transport: `stdio`
- SHA-256: `baf23f93b4d0ca927dffaf3d0dffc1af0e80518e1f3a3f127aee02be4870e904`

## 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**: 13/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - No install/post-install scripts declared.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **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 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1071 tokens (~214/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 Caption Checker MCP server?

Caption Checker ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, baf23f93b4d0ca927dffaf3d0dffc1af0e80518e1f3a3f127aee02be4870e904; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/markksantos/caption-checker/releases/download/v1.3.3/caption-checker-1.3.3.mcpb`
- SHA-256: `baf23f93b4d0ca927dffaf3d0dffc1af0e80518e1f3a3f127aee02be4870e904`

### Verify on macOS / Linux

```bash
echo "baf23f93b4d0ca927dffaf3d0dffc1af0e80518e1f3a3f127aee02be4870e904  caption-checker-1.3.3.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\caption-checker-1.3.3.mcpb).Hash -eq "baf23f93b4d0ca927dffaf3d0dffc1af0e80518e1f3a3f127aee02be4870e904"
```

## 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.

### 2026-11-04 (score 50, +1)

- [functional regression] Security disclosure: unverified → fail

### 2026-11-03 (score 49, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-11-02 (score 49, +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.

### 2026-10-30 (score 48, −1)

- [security regression] Provenance: unverified → fail
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Schema quality: pass → fail

### 2026-10-29 (score 49, +1)

- [security regression] Provenance: fail → unverified
- [functional regression] Security disclosure: fail → unverified

### 2026-10-27 (score 48, +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.

### 2026-10-24 (score 47, +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.

### 2026-10-22 (score 46, +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.

## MCP tools (5)

### `check_captions` (~190 tokens)

Check captions against a standard

Check an SRT or WebVTT caption file against Netflix English, the BBC subtitle guidelines or the DCMP Captioning Key: reading speed, characters a line, lines a caption, shortest and longest time on screen, gaps between captions, overlaps and unreadable timing lines. Pass a file path or the caption text itself. Read-only.

Input parameters:

- `fps` (number): Frame rate for frame-based gap checks (default 24).
- `include_advice` (boolean): Also list notes a standard words as a recommendation, not a limit.
- `path` (string): Path to a .srt or .vtt file on this machine.
- `standard` (string): Which standard to check against (default netflix).
- `text` (string): The caption file contents, when there is no file path.
- `vertical` (boolean): 9:16 video; the BBC allows three lines.

### `fix_captions` (~212 tokens)

Fix captions to a standard

Fix an SRT or WebVTT caption file to Netflix English, BBC or DCMP limits without changing a word or an in-time: rewraps lines that are too long or too many, pulls out-times off overlaps and gaps under the minimum, cuts captions to the longest time on screen, and extends out-times into free time when a caption is too short or reads too fast. Returns the fixed file as text (second content item) with a list of changes and of captions left for a person. Writes nothing to disk: save the fixed text yourself.

Input parameters:

- `fps` (number): Frame rate for frame-based gaps (default 24).
- `path` (string): Path to a .srt or .vtt file on this machine.
- `standard` (string): Which standard to fix to (default netflix).
- `text` (string): The caption file contents, when there is no file path.
- `vertical` (boolean): 9:16 video; the BBC allows three lines.

### `convert_captions` (~234 tokens)

Convert captions between SRT and WebVTT

Convert a SubRip (.srt) caption file to WebVTT (.vtt) or back, keeping every caption's text and timing. Italic, bold and underline are kept, SubRip {\anN} position codes and WebVTT line/align settings are translated, and whatever the other format cannot hold (font colours, voice tags, NOTE blocks) is listed. Returns the converted file as text (second content item). Writes nothing to disk: save it yourself.

Input parameters:

- `eol` (string): Line endings to write (default: the source's).
- `keep_ids` (boolean): SubRip to WebVTT: keep caption numbers as cue ids (default true).
- `path` (string): Path to a .srt or .vtt file on this machine.
- `speakers` (boolean): WebVTT to SubRip: write <v Name> voice tags as "Name: " instead of dropping them.
- `text` (string): The caption file contents, when there is no file path.
- `to` (string): Format to write (default: the other one).

### `retime_captions` (~344 tokens)

Retime captions

Fix caption timing that is out of sync with the video, in one of four ways: offset (move every caption, or every caption from number N on, by a time such as 1.5, -0:02.250 or 750ms), start_at (move the file so caption N starts at a given time), rate (captions timed for one frame rate on a video at another, e.g. 23.976 to 25, which drift later and later), or sync (pin two captions to their right start times and stretch everything else). Text, numbering and settings are kept; times are integer milliseconds. Returns the retimed file as text (second content item).

Input parameters:

- `from` (integer): With offset or start_at: leave the captions before this caption number alone.
- `offset` (string|number): Move captions by this much: seconds as a number, or 1.5, -0:02.250, 2m30s, 750ms. Negative is earlier.
- `path` (string): Path to a .srt or .vtt file on this machine.
- `rate` (object): Frame rate the captions were timed for (from) and the video's frame rate (to).
- `start_at` (object): Move the file so this caption starts at this time.
- `sync` (array): Two captions and the times they should start, ideally one near the start and one near the end.
- `text` (string): The caption file contents, when there is no file path.
- `to` (string): Format to write (default: the same as the source).

### `list_standards` (~33 tokens)

List caption standards

List the standards check_captions knows, with each limit it applies and the page the limit was read from.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/markksantos-caption-checker/caption-checker#diagnostics

## Score history

- 2026-11-05: 50
- 2026-11-04: 50
- 2026-11-03: 49
- 2026-11-02: 49
- 2026-11-01: 48
- 2026-10-31: 48
- 2026-10-30: 48
- 2026-10-29: 49
- 2026-10-28: 48
- 2026-10-27: 48
- 2026-10-26: 47
- 2026-10-25: 47
- 2026-10-24: 47
- 2026-10-23: 46
- 2026-10-22: 46
- 2026-10-21: 45
- 2026-10-20: 45
- 2026-10-19: 44

## Common questions

### What is the Caption Checker MCP server?

Caption Checker is an MCP server listed in the public MCP registry as io.github.markksantos/caption-checker. Check, fix, convert and retime SRT and WebVTT captions against Netflix, BBC and DCMP limits. This page covers its MCPB bundle (https://github.com/markksantos/caption-checker/releases/download/v1.3.3/caption-checker-1.3.3.mcpb).

### Is the Caption Checker MCP server safe to use?

Caption Checker scores 50 out of 100 on VerifyMCP. 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 Caption Checker MCP server expose?

Caption Checker exposes 5 tools: check_captions, fix_captions, convert_captions, retime_captions, list_standards. Their descriptions and schemas cost roughly 1,013 tokens of context every time the server is loaded.

### What licence is the Caption Checker MCP server under?

Caption Checker 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

- Repository: https://github.com/markksantos/caption-checker
- Website: https://www.markstudios.com/tools/caption-checker
- Changelog RSS feed: https://verifymcp.io/servers/markksantos-caption-checker/caption-checker.xml
- Changelog JSON feed: https://verifymcp.io/servers/markksantos-caption-checker/caption-checker.json
- HTML version of this page: https://verifymcp.io/servers/markksantos-caption-checker/caption-checker