Caption File Check MCP server
com.powmcp/caption-file-checkpowmcp.comstreamable-httpv0.3.3Scanned
Parse WebVTT, SRT, or TTML for conformance, timing, overlaps, line length, and reading speed.
2 tools: 1 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Caption File Check MCP server can do
The Caption File Check MCP server is published by powmcp.com, a domain the MCP Registry verified. It has 2 tools. It can create or change data (1 tool: caption_check), but cannot delete data. 1 tool only reads.
1 tool reads private data (caption_compare); 2 tools bring in text other people can write (caption_check and caption_compare); 2 tools can send data out of your system (caption_check and caption_compare). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 0.3.3.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
2 tools
Changes things 1Claude Code: ask
caption_checkPreflight one caption or subtitle file before delivery.Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "..., data URLs, FTP/SFTP, and URLs needing credentials, headers, or cookies are not supported...."
Description, as the server wrote it Preflight one caption or subtitle file before delivery. Attach a WebVTT (.vtt), SRT (.srt), or TTML/IMSC (.ttml/.xml) caption file in chat or give a publicly fetchable URL and it downloads the artifact under an SSRF-guarded, 2 MB-capped fetch, detects the format by content and the byte encoding and BOM, then parses it with the real spec engine (the WebVTT spec parser, a dedicated SRT parser, or the imscJS TTML/IMSC profile engine) and returns deterministic evidence: pass/fail, cue count, structural spec and IMSC profile-conformance errors, overlapping / negative / out-of-order / empty cues, per-line length, and per-cue and summary reading speed (CPS) against a named platform profile (netflix-adult-20, netflix-children-17, youtube, ebu-tt). It reports only source-file conformance, timing, encoding, and reading-speed facts against a dated profile. It does not judge translation quality, transcription accuracy, or synchronization against the video. An arbitrary XML or text file that is not a caption track returns an explicit unsupported-format error. Fetching and parsing a full-length track can take up to 60 seconds. WebVTT limitation: the parser drops payload-less cues; cue counts, indices, timing checks and comparisons cover retained cues only, not those omitted cues.
Annotations the server declares
- title: Caption Check
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
Only reads 1Show 1 read-only tool
caption_compareCompare exactly two caption or subtitle files under identical bounded checks: an original versus its translated track, before versus after a timing fix, or a format migration.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "caption_compare" says "compare": a word for reading.
What it can reach
- private-dataThe description's first sentence says "compare" and "file": it reads files.
- private-dataThe input names a file (input.files), and the tool reads: it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.urls), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Compare exactly two caption or subtitle files under identical bounded checks: an original versus its translated track, before versus after a timing fix, or a format migration. Attach two WebVTT, SRT, or TTML/IMSC caption files in chat or give two publicly fetchable URLs and it runs the same SSRF-guarded, 2 MB-capped preflight as caption_check on each, then aligns them by cue index and reports side-by-side pass status, detected-format and encoding differences, the cue-count delta, timing drift and overlap differences, reading-speed (CPS) regressions, structural-error deltas, and a winner only when the measured checks separate the two. Use caption_check for a single file. It reports only source-file conformance, timing, encoding, and reading-speed facts against a dated profile: never translation quality, transcription accuracy, or sync against the video. Fetching and parsing two live files can take up to 60 seconds. WebVTT limitation: the parser drops payload-less cues; cue counts, indices, timing checks and comparisons cover retained cues only, not those omitted cues.
Annotations the server declares
- title: Caption Compare
- readOnlyHint: true
- openWorldHint: true
- destructiveHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__caption-file-check__caption_compare"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:44 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://powmcp.com/.well-known/oauth-protected-resource/caption-file-check/mcp
- Authorization servers
- https://clerk.powmcp.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://powmcp.com/caption-file-check/mcp: tools/list returned 2 tools to an anonymous client, including caption_check (write)
Findings
Matches of fixed checks, with the text they matched.
- Infocaption_check
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "..., data URLs, FTP/SFTP, and URLs needing credentials, headers, or cookies are not supported...."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.3.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http caption-file-check https://powmcp.com/caption-file-check/mcpclaude mcp add --transport http caption-file-check https://powmcp.com/caption-file-check/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__caption-file-check__caption_check",
"mcp__caption-file-check__caption_compare"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as caption-file-check. Review it before you use it.
Capability tags behind 2 rules
- mcp__caption-file-check__caption_check untrusted-input, outbound
- mcp__caption-file-check__caption_compare private-data, untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.powmcp/caption-file-check/verify?hash=967aab038afb16e1b69fbc9eafb6742e1d091d6da5a0a69da903c448dcded30d" | jq -e '.changed == false'Pinned hash 967aab038afb, from Nov 10, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.powmcp/caption-file-check/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.powmcp/caption-file-check)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:00 UTC.
Caption File Check MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Caption File Check MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Caption File Check MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Caption File Check MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Caption File Check MCP server have?
- 2 tools: 1 write, 1 read. caption_check and caption_compare.
Does the Caption File Check MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Caption File Check MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): caption_check and caption_compare.
Has the Caption File Check MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.