Skip to content
anlyon.dev

Moodmark

io.github.janvodvarka/moodmarkjanvodvarkastreamable-httpv1.0.0Scanned

Let your AI agent build moodboards of real websites: save, search, tag and share design references.

9 tools: 6 change things and 3 only read.

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

Anlyon alternative

6 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →
Compare with similar serversMarkdownJSONReport this listing

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.

9 tools

Changes things 6Claude Code: ask
  • create_collectionCreate an empty collection (returns the existing one if the name is taken).No findings

    Why it is in this group

    • The name "create_collection" says "create": a word for a change.
    Description, as the server wrote it
    Create an empty collection (returns the existing one if the name is taken).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_design_briefTurn one saved reference into design.md: palette roles, typography, layout, components, a paste-ready prompt for AI builders (v0, Cursor, Lovable, Bolt) and CSS/Tailwind tokens.1 finding

    Why it is in this group

    • The name "get_design_brief" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "get_design_brief" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_design_brief" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Turn one saved reference into design.md: palette roles, typography, layout, components, a paste-ready prompt for AI builders (v0, Cursor, Lovable, Bolt) and CSS/Tailwind tokens. Cached on the bookmark; Premium only.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • save_websitesSave websites to the user's Moodmark library, optionally into a collection (created if missing).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "save_websites" says "save": a word for a change.

    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.urls): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Save websites to the user's Moodmark library, optionally into a collection (created if missing). Moodmark captures a screenshot, title, favicon, fonts and tech stack for each; the colour palette is extracted when the user opens the library. Up to 50 URLs per call. Already-saved sites are not duplicated.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • share_collectionTurn on the public, read-only link for a collection so it can be sent to a client (they can browse and vote).Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Turn on the public, read-only link for a collection so it can be sent to a client (they can browse and vote). Only call this when the user explicitly asks to share.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • suggest_tagsAI tag suggestions for up to 10 saved bookmarks, chosen from the user's own tags, each with a short reason.Reads text others writeNo 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.

    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
    AI tag suggestions for up to 10 saved bookmarks, chosen from the user's own tags, each with a short reason. Suggestions only; apply the ones that fit with update_bookmarks.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • update_bookmarksAdditive edits to saved bookmarks: add existing tags, append a note, add to a collection (created if missing).No findings

    Why it is in this group

    • The name "update_bookmarks" says "update": a word for a change.
    Description, as the server wrote it
    Additive edits to saved bookmarks: add existing tags, append a note, add to a collection (created if missing). Never removes anything the user set.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • list_collectionsThe user's collections with bookmark counts and links.No findings

    Why it is in this group

    • The name "list_collections" says "list": a word for reading.
    Description, as the server wrote it
    The user's collections with bookmark counts and links.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_tagsThe user's tags by category (industry, style, layout…).No findings

    Why it is in this group

    • The name "list_tags" says "list": a word for reading.
    Description, as the server wrote it
    The user's tags by category (industry, style, layout…). Only these names can be applied when saving.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • search_libraryFind bookmarks the user already saved — by text (title, URL, note, tags, fonts, tech), colour family, tags or collection.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "search_library" 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 description's first sentence says "find" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Find bookmarks the user already saved — by text (title, URL, note, tags, fonts, tech), colour family, tags or collection. Returns newest first.

    Annotations the server declares

    • readOnlyHint: 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.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound 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 out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__moodmark__save_websites"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warnget_design_brief

    The server marks "get_design_brief" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_design_brief" says "get": a word for reading.

    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.

All changes to this server

Install

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

claude mcp add --transport http moodmark https://app.moodmark.design/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http moodmark https://app.moodmark.design/mcp --header 'Authorization: <your-authorization>'

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__moodmark__search_library",
      "mcp__moodmark__list_collections",
      "mcp__moodmark__list_tags"
    ],
    "ask": [
      "mcp__moodmark__save_websites",
      "mcp__moodmark__create_collection",
      "mcp__moodmark__get_design_brief",
      "mcp__moodmark__update_bookmarks",
      "mcp__moodmark__suggest_tags",
      "mcp__moodmark__share_collection"
    ],
    "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 moodmark. Review it before you use it.

Capability tags behind 4 rules
  • mcp__moodmark__save_websites untrusted-input, outbound
  • mcp__moodmark__search_library private-data, untrusted-input
  • mcp__moodmark__suggest_tags untrusted-input
  • mcp__moodmark__share_collection 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://anlyon.dev/api/v1/servers/io.github.janvodvarka/moodmark/verify?hash=4d33acc0aa76db8295e5680f7e3d566750e358f471f4a83621211ea9253f1752" | jq -e '.changed == false'

Pinned hash 4d33acc0aa76, from Oct 23, 2026, 08:18 UTC.

Watch

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

https://anlyon.dev/servers/io.github.janvodvarka/moodmark/changes.xml

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

Badge

anlyon.dev badge for io.github.janvodvarka/moodmark
[![anlyon.dev](https://anlyon.dev/badge/io.github.janvodvarka/moodmark.svg)](https://anlyon.dev/servers/io.github.janvodvarka/moodmark)

Source: MCP Registry. Synced Oct 23, 2026, 08:17 UTC.