Skip to content

Thread Kit: posts that fit every network MCP server

dev.workers.agent-arena-base.thread-kit/thread-kitthread-kit.agent-arena-base.workers.devstreamable-httpv1.5.0Scanned

Free post-length counter (X, Bluesky, Farcaster, Mastodon, Threads); paid thread split + AI writers

8 tools: 1 do something that can't be undone, 6 change things and 1 only read.

Tools: 0 delete, 1 irreversible, 6 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 1
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • 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 Thread Kit: posts that fit every network MCP server can do

The Thread Kit: posts that fit every network MCP server is published by thread-kit.agent-arena-base.workers.dev, a domain the MCP Registry verified. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (payment_options) and create or change data (6 tools: split_thread, check_post_length, write_thread_from_article, write_short_video_script and 2 more), but cannot delete data. 1 tool only reads.

3 tools bring in text other people can write (write_thread_from_article, write_short_video_script and count_post_length); 1 tool can send data out of your system (check_post_length).

The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 21, 2026, version 1.5.0.

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.

8 tools

Can't be undone 1Claude Code: ask
  • payment_optionsFREE.1 finding

    Why it is in this group

    • The name "payment_options" says "payment": a word that usually means money moves, which cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "payment_options" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "payment_options" says "payment": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    FREE. Receiving address, prices and how to pay the paid tools: x402 over MCP (USDC on Base, per call), or the same endpoints over plain HTTP x402 / MPP.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 6Claude Code: ask
  • check_post_lengthFull check of one post for a network: valid or not, exact length in that network's unit, remaining, issues (over the limit, byte cap, too many links, invalid characters, NFC) and a…Can send data out1 finding

    Why it is in this group

    • The name "check_post_length" says "post": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe name "check_post_length" says "post": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "check_post_length" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "check_post_length" says "post": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Full check of one post for a network: valid or not, exact length in that network's unit, remaining, issues (over the limit, byte cap, too many links, invalid characters, NFC) and a "fitted" version cut at a sentence or word boundary with an ellipsis when it is too long. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. For the length alone use the free count_post_length. PAID: $0.001 per call in USDC on Base via x402 over MCP (see payment_options).

    Annotations the server declares

    • title: Check one post and get a version that fits
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • network_rulesFREE.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    FREE. Limits, counting units and sources for X, Bluesky, Farcaster, Mastodon and Threads (Meta).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • split_threadSplit long text into a thread where every post fits the network's limit, counted the way that network counts.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Split long text into a thread where every post fits the network's limit, counted the way that network counts. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. Breaks at paragraph, sentence, clause, then word boundaries (CJK-aware), never inside a URL or @mention, adds n/N numbering that is included in the count, and re-checks every post. Returns posts with their lengths. Pure computation. PAID: $0.002 per call in USDC on Base via x402 over MCP (see payment_options).

    Annotations the server declares

    • title: Split text into a thread that fits (X, Bluesky, Farcaster, Mastodon, Threads)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • write_short_video_scriptTurn an article, notes or product description into a 15/30/45/60-second vertical-video script: hook first, then beats with voiceover, on-screen text and a shot description (usable …Reads text others write1 finding

    Why it is in this group

    • The name "write_short_video_script" says "write": 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.

    Findings

    • Warn

      The server marks "write_short_video_script" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "write_short_video_script" says "write": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Turn an article, notes or product description into a 15/30/45/60-second vertical-video script: hook first, then beats with voiceover, on-screen text and a shot description (usable as a text-to-video prompt), plus title, caption, up to 5 hashtags and SRT subtitles. Timed from speaking rate and trimmed to fit (+10%). No video or voice is generated. A failed generation is not charged. PAID: $0.020 per call in USDC on Base via x402 over MCP (see payment_options).

    Annotations the server declares

    • title: Write a timed short-video script (TikTok, Reels, YouTube Shorts) with SRT subtitles (AI)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • write_thread_from_articleTurn an article, blog post, notes, changelog or transcript into a ready-to-post thread (hook first, one point per post, wrap-up last) for X, Bluesky, Farcaster, Mastodon or Threads…Reads text others write1 finding

    Why it is in this group

    • The name "write_thread_from_article" says "write": 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.

    Findings

    • Warn

      The server marks "write_thread_from_article" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "write_thread_from_article" says "write": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Turn an article, blog post, notes, changelog or transcript into a ready-to-post thread (hook first, one point per post, wrap-up last) for X, Bluesky, Farcaster, Mastodon or Threads. An open model on Cloudflare Workers AI writes it; Thread Kit re-measures and re-splits every post so each one fits, removes links that are not in the source and flags numbers that are not in it. A failed generation is not charged. PAID: $0.010 per call in USDC on Base via x402 over MCP (see payment_options).

    Annotations the server declares

    • title: Write a thread from an article or notes (AI)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • writing_examplesFREE.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    FREE. A hand-written example of what write_thread_from_article and write_short_video_script return, with the input that produced it. No model call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 1Show 1 read-only tool
  • count_post_lengthFREE.Reads text others writeNo findings

    Why it is in this group

    • The name "count_post_length" says "count": a word for reading.

    What it can reach

    • untrusted-inputThe name "count_post_length" says "count" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    FREE. Exact length of one post for X, Bluesky, Farcaster, Mastodon or Threads (Meta), in that network's own unit, with the limit, remaining and whether it fits. X: weighted, CJK and emoji count 2, every link 23, limit 280. Bluesky: 300 graphemes and 3000 bytes. Farcaster: UTF-8 bytes, 320 per cast (1024 long cast). Mastodon: 500, links 23. Threads (Meta): 500, emoji count as their UTF-8 bytes. Use it before posting; if it does not fit, check_post_length returns a shortened version and split_thread a thread.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: 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.

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 out1
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 21, 2026, 19:25 UTC, unchanged since Nov 21, 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
10
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 10 tools that change things (1 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://thread-kit.agent-arena-base.workers.dev/mcp: tools/list returned 11 tools to an anonymous client, including payment_options (irreversible), split_thread (write), check_post_length (write), write_thread_from_article (write), write_short_video_script (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

4 warn
  • The server marks "check_post_length" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "check_post_length" says "post": a word for a change.

    What this check looks for
  • The server marks "write_thread_from_article" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "write_thread_from_article" says "write": a word for a change.

    What this check looks for
  • The server marks "write_short_video_script" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "write_short_video_script" says "write": a word for a change.

    What this check looks for
  • The server marks "payment_options" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "payment_options" says "payment": a word that usually means money moves, which cannot be taken back.

    What this check looks for

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

claude mcp add --transport http thread-kit https://thread-kit.agent-arena-base.workers.dev/mcp
claude mcp add --transport http thread-kit https://thread-kit.agent-arena-base.workers.dev/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__thread-kit__count_post_length"
    ],
    "ask": [
      "mcp__thread-kit__split_thread",
      "mcp__thread-kit__check_post_length",
      "mcp__thread-kit__write_thread_from_article",
      "mcp__thread-kit__write_short_video_script",
      "mcp__thread-kit__network_rules",
      "mcp__thread-kit__writing_examples",
      "mcp__thread-kit__payment_options"
    ],
    "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 thread-kit. Review it before you use it.

Capability tags behind 4 rules
  • mcp__thread-kit__check_post_length outbound
  • mcp__thread-kit__write_thread_from_article untrusted-input
  • mcp__thread-kit__write_short_video_script untrusted-input
  • mcp__thread-kit__count_post_length 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/dev.workers.agent-arena-base.thread-kit/thread-kit/verify?hash=82349e34ae999ac735508a49ca8829f3791897436c29a24574b516cabe1d4c49" | jq -e '.changed == false'

Pinned hash 82349e34ae99, from Nov 21, 2026, 09:17 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.workers.agent-arena-base.thread-kit/thread-kit/changes.xml

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

Badge

Anlyon Radar badge for dev.workers.agent-arena-base.thread-kit/thread-kit
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.agent-arena-base.thread-kit/thread-kit.svg)](https://radar.anlyon.com/servers/dev.workers.agent-arena-base.thread-kit/thread-kit)

Source: MCP Registry. Synced Nov 21, 2026, 09:17 UTC.

Thread Kit: posts that fit every network MCP server: questions and answers

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

Is the Thread Kit: posts that fit every network MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 7 of which can change, send or delete something, and 4 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 Thread Kit: posts that fit every network MCP server delete data?

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

Can the Thread Kit: posts that fit every network MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: payment_options.

What tools does the Thread Kit: posts that fit every network MCP server have?

8 tools: 1 irreversible, 6 write, 1 read. payment_options, split_thread, check_post_length, write_thread_from_article, write_short_video_script, network_rules, writing_examples and count_post_length.

Does the Thread Kit: posts that fit every network MCP server need sign-in or OAuth?

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

Does the Thread Kit: posts that fit every network MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_post_length.

Has the Thread Kit: posts that fit every network MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.