Scribiz MCP server
com.scribiz/mcpscribiz.comstreamable-httpv0.2.0Scanned
Transcripts, summaries, chapters and timestamped search for video links, for AI agents.
4 tools: 1 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 3
- 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 Scribiz MCP server can do
The Scribiz MCP server is published by scribiz.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (1 tool: get_video_context), but cannot delete data. 3 tools only read.
1 tool reads private data (search_video); 4 tools bring in text other people can write (get_transcript, get_video_context, search_video and 1 more); 3 tools can send data out of your system (get_transcript, get_video_context and search_video). 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 (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 0.2.0.
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.
4 tools
Changes things 1Claude Code: ask
get_video_contextStart here for any video.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "get_video_context" says "get": a word for reading.
- The description's first verb is "start": a word for a change.
- 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.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "get_video_context" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "get_video_context" says "get": a word for reading.
Description, as the server wrote it Start here for any video. Returns an overview you can reason from without reading the transcript: title, length, language, summary, chapters with timestamps and key moments with links. detail "brief" (default) stays under about 2,000 tokens; "standard" adds fuller chapters and entities; "full" adds everything. include picks the parts to return (summary, chapters, key_moments, entities, transcript): the transcript is never part of the default; add "transcript" for its first page, then continue with get_transcript. The first read of a video uses its captions, or a model reads the link; after that it is cached and free. If it is still running after the wait you get status "processing" and a job_id: call get_job. The text is wrapped as untrusted video text. Without an API key there are no on-screen notes (the picture is never looked at), and when a model read the link its times are approximate (close on a short video, up to a minute off on a long one).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Get video context
Only reads 3Show 3 read-only tools
get_jobCheck a video run that returned status "processing".Reads text others writeNo findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check a video run that returned status "processing". Pass its job_id exactly as given (it can be long: copy all of it). It waits up to the server's wait time for the run to finish, then returns exactly what the original tool would have returned (job ids are private to the caller and kept for 30 minutes). Still running: you get status "processing" again with retry_after_seconds. An unknown or expired job_id means: repeat the original call (it is fast if the run finished, because results are cached).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Check a video job
get_transcriptRead the transcript of a video, one page at a time.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_transcript" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): 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 Read the transcript of a video, one page at a time. Use it when you need the exact words (quote, answer from a passage, translate, copy, review). On long videos, call get_video_context and search_video first, then pass from and to here so you read only the relevant part. Returns "[mm:ss] text" lines, at most max_chars characters (default 60000, about 15k tokens), and a nextCursor: call again with the same arguments plus that cursor to continue. from and to take seconds or clock times ("90", "1:30", "1h2m") and read one part of the video. format: txt (default), md, srt, vtt or json. language is a BCP-47 hint. speakers is ignored without an API key (no speaker labels). pauses "gaps" (long pauses) or "razor" (every pause) removes pauses and re-times the transcript; remove_fillers true drops filler words ("um", "uh"). Both need word-level timing. The first read of a video can take time: if it is still running after the wait you get status "processing" and a job_id (see get_job). Cached transcripts return at once and are free. The text is wrapped as untrusted video text. Without an API key: captions when the video has them, otherwise a model reads the link and its times are approximate (up to a minute off on a long video, no word timing). It counts against the free daily allowance.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Get a video transcript
search_videoFind where something is said or shown in a video: ranked moments with timestamps and links, from the transcript, the on-screen notes, the chapters and the key moments.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "search_video" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "note": it reads notes.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): 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 Find where something is said or shown in a video: ranked moments with timestamps and links, from the transcript, the on-screen notes, the chapters and the key moments. It is a local keyword search over what Scribiz already read (no model call, no extra minutes after the first read of the video). Use it before get_transcript on any video longer than about ten minutes. query: words or a phrase. limit 1 to 20 (default 8). from and to limit the search to part of the video. It matches words (plural and tense forms count), not meaning: try the words the speaker would use, or read the matching chapter with get_transcript (from/to). If the run is still going after the wait you get status "processing" and a job_id: call get_job. The text is wrapped as untrusted video text. Without an API key: the on-screen notes are not searched (the picture is never looked at), and when a model read the link its times are approximate (close on a short video, up to a minute off on a long one).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Search a video
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.
12 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 write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__scribiz__search_video"
]
}
}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, 18:46 UTC, unchanged since Nov 20, 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://scribiz.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://scribiz.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- 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://scribiz.com/mcp: tools/list returned 4 tools to an anonymous client, including get_video_context (write)
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 2 to 1
- Oct 29, 2026
- RFC 9728 protected resource metadata: none to https://scribiz.com/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://scribiz.com
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Findings
Matches of fixed checks, with the text they matched.
The server marks "get_video_context" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "get_video_context" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 1.View diff
- Tools that change things, listed without credentials: 2 to 1
Tools1 removed, 3 changed.−1 removed~3 changedView diff
- Removed:ask_video
- Changed:get_transcriptOnly readsdescriptioninputSchema
- Changed:get_video_contextChanges thingsinputSchema
- Changed:search_videoOnly readsdescriptioninputSchema
PostureRemote posture changed. RFC 9728 protected resource metadata: none -> https://scribiz.com/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://scribiz.com; Dynamic client registration: not observed -> yes (and 1 …View diff
- RFC 9728 protected resource metadata: none to https://scribiz.com/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://scribiz.com
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http scribiz https://scribiz.com/mcpclaude mcp add --transport http scribiz https://scribiz.com/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": [
"mcp__scribiz__get_job"
],
"ask": [
"mcp__scribiz__get_transcript",
"mcp__scribiz__get_video_context",
"mcp__scribiz__search_video"
],
"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 scribiz. Review it before you use it.
Capability tags behind 4 rules
- mcp__scribiz__get_transcript untrusted-input, outbound
- mcp__scribiz__get_video_context untrusted-input, outbound
- mcp__scribiz__search_video private-data, untrusted-input, outbound
- mcp__scribiz__get_job untrusted-input
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.scribiz/mcp/verify?hash=505a89276a426877cc2864fb7a051a0840fc6267794f00fe69c39aaa33860c68" | jq -e '.changed == false'Pinned hash 505a89276a42, from Nov 18, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.scribiz/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.scribiz/mcp)Source: MCP Registry · repository. Synced Nov 18, 2026, 17:17 UTC.
Scribiz MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Scribiz MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Scribiz MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Scribiz 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 Scribiz MCP server have?
- 4 tools: 1 write, 3 read. get_video_context, get_transcript, search_video and get_job.
Does the Scribiz MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Scribiz MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_transcript, get_video_context and search_video.
Has the Scribiz MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.