Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Subtitle Toolkit

REMOTE · SUBTITLE-MCP.TOOLBOXES.TOP

Convert, clean, retime and validate SRT, WebVTT, ASS/SSA, SBV and TTML subtitles. 8 tools.

0 this week 76 Trust /100

Last scanned (20 hours ago)

Scores higher than 65% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Documents and Files

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability81
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1451 tokens (~161/item across 9 items; 8 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "merge_subtitles" implies "merge" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 22 Oct 26 0
    • Stability: 0.97 → pass security
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://subtitle-mcp.toolboxes.top/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=toolboxes.top CN=WE1,O=Google Trust Services,C=US 20 Nov 2026 18 Feb 2027 ECDSA 256 ECDSA-SHA256 c27c5d7a60d8af1a0e19bfd006386e3b
SANs: toolboxes.top, subtitle-mcp.toolboxes.top, *.subtitle-mcp.toolboxes.top
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of subtitle-mcp.toolboxes.top. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
top. DS published 41508 13 Verified
toolboxes.top. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://subtitle-mcp.toolboxes.top/mcp Verified 200
http (plaintext) http://subtitle-mcp.toolboxes.top/mcp HTTPS enforced 301 https://subtitle-mcp.toolboxes.top/mcp
MCP tools · 8 exposed · ~1,189 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_subtitle_timing ~150

Audit subtitle readability and produce a report: reading speed (CPS), cue durations that are too short or too long, lines that are too wide, more than two lines, and overlapping cues. Returns a formatted report listing every flagged cue.

NameTypeReqDescription
contentstringyesThe full subtitle file text.
max_cpsnumber–Max characters per second. Default 20.
max_duration_secondsnumber–Maximum cue duration in seconds. Default 7.
max_line_lengthnumber–Max characters per line. Default 42.
min_duration_secondsnumber–Minimum cue duration in seconds. Default 0.833 (Netflix 5/6s).

No output schema declared.

No examples provided.

clean_subtitles ~194

Strip noise from auto-generated subtitles: HTML/WebVTT tags, ASS override codes, music and sound-effect cues, speaker labels, empty cues and duplicate lines. Returns the subtitle file in SRT or WebVTT.

NameTypeReqDescription
contentstringyesThe full subtitle file text.
drop_duplicatesboolean–Drop cues whose text was already seen. Default false.
drop_emptyboolean–Drop cues that become empty after cleaning. Default true.
remove_sound_cuesboolean–Strip [Music], [Applause], ♪ ... ♪ and similar. Default true.
remove_speaker_labelsboolean–Strip leading "SPEAKER:" prefixes. Default false — enable only if you want them gone.
remove_tagsboolean–Strip HTML/WebVTT tags and ASS override codes. Default true.
tostring–Output format. Default: same as the input.

No output schema declared.

No examples provided.

convert_subtitle ~145

Convert subtitle text between formats. Reads SRT, WebVTT, ASS/SSA, YouTube SBV and TTML/DFXP; writes SRT, WebVTT, ASS, CSV or plain text. Format is auto-detected unless `from` is given.

NameTypeReqDescription
contentstringyesThe full subtitle file text.
dedupeboolean–Only for to="text": collapse consecutive identical lines (rolling-caption transcripts repeat lines). Default false.
fromstring–Source format (default "auto" = detect).
tostringyesTarget format. `text` = plain transcript, one line per cue, no timecodes.

No output schema declared.

No examples provided.

fix_subtitle_encoding ~143

Repair mojibake — text where UTF-8 bytes were decoded as a single-byte encoding (cp1252/Latin-1 or cp1251). Symptoms: "é", "’", "привет". Returns the repaired text and how many passes were applied.

NameTypeReqDescription
contentstringyesThe garbled subtitle text.
read_asstring–Which encoding the file was wrongly read as. Default "auto" (tries cp1252 then cp1251).
twiceboolean–Set true when the text was mis-decoded twice (nested mojibake). Default false.

No output schema declared.

No examples provided.

merge_subtitles ~112

Append one subtitle track after another (CD1 + CD2, or a second language track). The second track is offset so it starts after the last cue of the first, plus an optional gap.

NameTypeReqDescription
append_contentstringyesThe subtitle file text to append.
contentstringyesThe first subtitle file text.
gap_secondsnumber–Extra gap between the two tracks, in seconds. Default 0.
tostring–Output format. Default: same as the input.

No output schema declared.

No examples provided.

retime_subtitles ~178

Fix subtitle timing. Use offset_seconds for a uniform shift (whole track early/late). Use ratio, or from_fps/to_fps, for progressive drift caused by a frame-rate mismatch. Pass exactly one of the three.

NameTypeReqDescription
contentstringyesThe full subtitle file text.
from_fpsnumber–The frame rate the subtitles were authored for (used with to_fps).
offset_secondsnumber–Shift every cue by this many seconds. Negative = earlier. e.g. -2.5
rationumber–Scale all timings by this factor (new = old x ratio). e.g. 1.0427 for a 25→23.976 fps fix.
to_fpsnumber–The frame rate of the actual video (used with from_fps).

No output schema declared.

No examples provided.

split_subtitles ~130

Split one subtitle track into two parts at a given timecode, keeping original timecodes. Use the `at` argument plus `part` to fetch either half.

NameTypeReqDescription
atstringyesSplit point. Accepts "45:00", "1:02:03", "90" (seconds) or "1:02:03.500".
contentstringyesThe full subtitle file text.
partstring–Which half to return. Default "a" (before the split point).
tostring–Output format. Default: same as the input.

No output schema declared.

No examples provided.

text_to_subtitles ~137

Turn a plain transcript (one line per caption) into an SRT file with evenly spaced timecodes. Timing is a starting point, not a real transcription — say so when you present the result.

NameTypeReqDescription
contentstringyesPlain text, one caption per line. Blank lines are skipped.
duration_secondsnumber–Seconds each cue stays on screen. Default 2.5.
max_chars_per_cuenumber–Split longer lines into several cues at word boundaries. Default 0 = never split.
start_secondsnumber–Timecode of the first cue, in seconds. Default 0.

No output schema declared.

No examples provided.

Install

How do I install the Subtitle Toolkit MCP server?

Subtitle Toolkit is a hosted endpoint at https://subtitle-mcp.toolboxes.top/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.

remote · subtitle-mcp.toolboxes.top

# add to Claude Code
claude mcp add --transport http top-toolboxes-subtitle-toolkit 'https://subtitle-mcp.toolboxes.top/mcp'
Common questions

What is the Subtitle Toolkit MCP server?

Subtitle Toolkit is an MCP server listed in the public MCP registry as top.toolboxes/subtitle-toolkit. Convert, clean, retime and validate SRT, WebVTT, ASS/SSA, SBV and TTML subtitles. 8 tools. This page covers its hosted endpoint (https://subtitle-mcp.toolboxes.top/mcp).

Is the Subtitle Toolkit MCP server safe to use?

Subtitle Toolkit scores 76 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 Subtitle Toolkit MCP server expose?

Subtitle Toolkit exposes 8 tools: convert_subtitle, clean_subtitles, retime_subtitles, check_subtitle_timing, merge_subtitles, and 3 more. Their descriptions and schemas cost roughly 1,189 tokens of context every time the server is loaded.

Does the Subtitle Toolkit MCP server require authentication?

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

Is the Subtitle Toolkit MCP server still maintained?

Subtitle Toolkit 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 Subtitle Toolkit MCP server?

VerifyMCP ran 12 checks on Subtitle Toolkit, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Subtitle Toolkit: Authorization. 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.