Skip to content

agent-media-toolkit MCP server

io.github.krakonjac300-pixel/agent-media-toolkitkrakonjac300-pixelstreamable-httpv1.0.0Scanned

15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more.

15 tools: 11 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 11 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

11 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 agent-media-toolkit MCP server can do

The agent-media-toolkit MCP server is published by the GitHub account krakonjac300-pixel. It has 15 tools. It can create or change data (11 tools: news, repurpose, translate, script and 7 more), but cannot delete data. 4 tools only read.

3 tools bring in text other people can write (search, extract and summarize); 4 tools can send data out of your system (extract, summarize, media_info and 1 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.0.0.

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.

15 tools

Changes things 11Claude Code: ask
  • edit_clipCut a time range into a finished 9:16 captioned short.No findings

    Why it is in this group

    • The name "edit_clip" says "edit": a word for a change.
    Description, as the server wrote it
    Cut a time range into a finished 9:16 captioned short. Premium (via x402).
  • media_infoMetadata (title, duration, uploader, views) for a media URL — no download.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Metadata (title, duration, uploader, views) for a media URL — no download.
  • moderateContent-safety classification: flagged?, categories, severity, reason.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Content-safety classification: flagged?, categories, severity, reason.
  • newsRecent news for a query/niche.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Recent news for a query/niche. Returns items with title, url, snippet, date, source.
  • package_postPlatform-optimized title, description, and hashtags for a clip.Can send data outNo findings

    Why it is in this group

    • The name "package_post" says "post": a word for a change.

    What it can reach

    • outboundThe name "package_post" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Platform-optimized title, description, and hashtags for a clip. Premium (via x402).
  • repurposeTurn text into social assets: thread, summary, titles, hashtags.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Turn text into social assets: thread, summary, titles, hashtags.
  • scriptWrite a short-form video script (hook, beats, cta) for a topic.No findings

    Why it is in this group

    • The description's first verb is "write": a word for a change.
    Description, as the server wrote it
    Write a short-form video script (hook, beats, cta) for a topic.
  • subtitlesAudio/video URL -> .srt/.vtt subtitle file.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Audio/video URL -> .srt/.vtt subtitle file. Premium (via x402).
  • transcribeTranscribe an audio/video URL to timestamped text.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Transcribe an audio/video URL to timestamped text. Premium (via x402).
  • translateTranslate text into target_lang (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Translate text into target_lang (e.g. 'Spanish', 'ja').
  • voiceoverText -> natural MP3 narration.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Text -> natural MP3 narration. Returns a download URL.
Only reads 4Show 4 read-only tools
  • extractFetch a web page and return clean main-content text (no nav/ads/boilerplate).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "fetch" and "web": it reads web pages, which anyone can write.
    • 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
    Fetch a web page and return clean main-content text (no nav/ads/boilerplate).
  • find_clipsFind viral clip candidates in a long video with scores.No findings

    Why it is in this group

    • The name "find_clips" says "find": a word for reading.
    Description, as the server wrote it
    Find viral clip candidates in a long video with scores. Premium (via x402).
  • summarizeSummarize text OR a web page (give text or url).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "summarize" says "summarize": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "summarize" and "web": it reads web pages, which anyone can write.
    • 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
    Summarize text OR a web page (give text or url). style: paragraph|bullets.

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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:07 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
11
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://podcast-shorts-a2a-production.up.railway.app/mcp/: tools/list returned 15 tools to an anonymous client, including news (write), repurpose (write), translate (write), script (write), moderate (write) and 6 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-media-toolkit https://podcast-shorts-a2a-production.up.railway.app/mcp/
claude mcp add --transport http agent-media-toolkit https://podcast-shorts-a2a-production.up.railway.app/mcp/

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-media-toolkit__search",
      "mcp__agent-media-toolkit__find_clips"
    ],
    "ask": [
      "mcp__agent-media-toolkit__news",
      "mcp__agent-media-toolkit__extract",
      "mcp__agent-media-toolkit__summarize",
      "mcp__agent-media-toolkit__repurpose",
      "mcp__agent-media-toolkit__translate",
      "mcp__agent-media-toolkit__script",
      "mcp__agent-media-toolkit__moderate",
      "mcp__agent-media-toolkit__media_info",
      "mcp__agent-media-toolkit__voiceover",
      "mcp__agent-media-toolkit__package_post",
      "mcp__agent-media-toolkit__transcribe",
      "mcp__agent-media-toolkit__subtitles",
      "mcp__agent-media-toolkit__edit_clip"
    ],
    "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 agent-media-toolkit. Review it before you use it.

Capability tags behind 5 rules
  • mcp__agent-media-toolkit__search untrusted-input
  • mcp__agent-media-toolkit__extract untrusted-input, outbound
  • mcp__agent-media-toolkit__summarize untrusted-input, outbound
  • mcp__agent-media-toolkit__media_info outbound
  • mcp__agent-media-toolkit__package_post 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/io.github.krakonjac300-pixel/agent-media-toolkit/verify?hash=7371eb79c577f86366ab23f97bc5c0f1836080bee26f2edfddcec7f1d80c41ae" | jq -e '.changed == false'

Pinned hash 7371eb79c577, from Nov 20, 2026, 01:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.krakonjac300-pixel/agent-media-toolkit/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.krakonjac300-pixel/agent-media-toolkit
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.krakonjac300-pixel/agent-media-toolkit.svg)](https://radar.anlyon.com/servers/io.github.krakonjac300-pixel/agent-media-toolkit)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:37 UTC.

agent-media-toolkit MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the agent-media-toolkit MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 11 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the agent-media-toolkit MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the agent-media-toolkit 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 agent-media-toolkit MCP server have?

15 tools: 11 write, 4 read. news, repurpose, translate, script, moderate, media_info, voiceover, package_post and 7 more.

Does the agent-media-toolkit MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the agent-media-toolkit MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract, summarize, media_info and package_post.

Has the agent-media-toolkit MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.