Skip to content

A2UI Atomic Catalog MCP server

ai.a2uicatalog/cataloga2uicatalog.aistreamable-httpv1.0.0Scanned

500+ typed UI atoms an agent composes into real rendered interfaces. Free, no API key.

40 tools: 3 can delete or cancel things, 1 do something that can't be undone, 24 change things and 12 only read.

Tools: 3 delete, 1 irreversible, 24 write, 12 read.
  • Reads private data · 2
  • Reads text others write · 16
  • Can send data out · 5
  • 7 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here can delete or cancel things and 1 does something that can't be undone. 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 A2UI Atomic Catalog MCP server can do

The A2UI Atomic Catalog MCP server is published by a2uicatalog.ai, a domain the MCP Registry verified. It has 40 tools. It can delete or cancel things (3 tools: unpublish_url, delete_reading and unlink_slack_account), do things that cannot be undone, such as sending, paying or publishing (publish_url) and create or change data (24 tools: required_catalogs, build_multi_page_surface, make_surface_url, render_surface and 20 more). 12 tools only read.

2 tools read private data (render_ping and deck_schema); 16 tools bring in text other people can write (find_atoms, preview_url, sketch_agent_start and 13 more); 5 tools can send data out of your system (publish_url, emit_runbook_surface, save_reading and 2 more). 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 7 findings (long-description, annotation-conflict and tool-shadowing). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 10, 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.

40 tools

Deletes or cancels 3Claude Code: deny
  • delete_readingPermanently remove one or more of the reader's saved readings from their History.Reads text others writeNo findings

    Why it is in this group

    • The name "delete_reading" says "delete": a word for removing or ending something.
    • The description says "Permanently remove".
    • The server marks it destructive (destructiveHint: true).

    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
    Permanently remove one or more of the reader's saved readings from their History. Takes an array so the Workspace's multi-select can delete a batch in one call rather than one round trip per row. Ids that don't exist (or belong to someone else's history) are silently skipped — the response's `deleted` count says how many rows actually went, never assume it equals the number of ids you sent.

    Annotations the server declares

    • title: delete_reading
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • unpublish_urlDelete a published short link before its TTL using the delete_token returned by publish_url.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    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
    Delete a published short link before its TTL using the delete_token returned by publish_url.

    Annotations the server declares

    • title: unpublish_url
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
Can't be undone 1Claude Code: ask
  • publish_urlSTORES the payload server-side and returns a SHORT shareable link.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "publish_url" says "publish": a word for a change that another call does not undo.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "publish_url" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    STORES the payload server-side and returns a SHORT shareable link. Opt-in only: requires acknowledge_storage=true — confirm with the user first that they accept operator-hosted storage (ONE WEEK retention on the public tier, revocable earlier via the returned delete_token; anyone with the link can view). target "play" (default) renders in the a2uicatalog playground by reference (no URL size ceiling); target "gas" makes the short link redirect to the public Apps Script renderer. For storage in the USER's own account use emit_deployment; for nothing-stored links use preview_url.

    Annotations the server declares

    • title: publish_url
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 24Claude Code: ask
  • amigaOpen a real, cycle-exact Amiga 500 emulator in-chat (MCP Apps hosts only).1 finding

    Why it is in this group

    • The description's first verb is "open": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "amiga" 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 description's first verb is "open": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Open a real, cycle-exact Amiga 500 emulator in-chat (MCP Apps hosts only). Boots straight into AROS, a free open-source environment (no copyrighted Kickstart ROM involved), with a public-domain Amiga game already loaded and running. This is a fixed, self-contained retro-computing demo -- there is nothing to configure and no arguments to give it; call it when someone wants to see or play with a real emulated Amiga. On a host without MCP Apps support this says so as text; an emulator has no useful non-visual form.

    Annotations the server declares

    • title: amiga
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • build_multi_page_surfaceBuild a multi-section A2UI app from raw title+content sections — you never estimate size or decide how to split; each section becomes its own independently-encoded page (no shared …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
    Build a multi-section A2UI app from raw title+content sections — you never estimate size or decide how to split; each section becomes its own independently-encoded page (no shared hub, so per-page size never grows with page count — genuinely unlimited sections). Returns the first page's `url` plus a `pages` array ([{heading, url}]) for every section — present that list to the user yourself (e.g. numbered links); pages do not cross-link to each other. Prefer this over make_surface_url for multi-section content.

    Annotations the server declares

    • title: build_multi_page_surface
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • deck_buildBuild a PowerPoint (.pptx) file from a scene list or an A2UI payload.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
    Build a PowerPoint (.pptx) file from a scene list or an A2UI payload. Deterministic (same input, same bytes), nothing is stored or fetched, text is fitted with real font metrics and the file is linted (overlap, bounds, contrast, alt text). Returns the file as an embedded resource plus a report: errors, lint, warnings and unsupported atoms. Opens in PowerPoint and Google Slides (checked in Google Slides). Demo limit: 10 builds a day per connection.

    Annotations the server declares

    • title: Build a PPTX
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • diagram_studioDraw a diagram in-chat with the full Diagram Studio interface (MCP Apps hosts only; it opens fullscreen where the host allows it).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
    Draw a diagram in-chat with the full Diagram Studio interface (MCP Apps hosts only; it opens fullscreen where the host allows it). YOU write the diagram; nothing is generated server-side and nothing is stored. PREFER `graph`: give vertices (id, label, type start|process|decision|database|cloud|end) and edges (source, target, optional label). The person then gets the whole studio: they can switch the same graph between Mermaid, D2, PlantUML and draw.io, flip its direction, zoom, copy the code, open it in the real draw.io editor with one click, and edit nodes and connections themselves (their edits come back to you). Use `syntax` with `source` instead only for diagrams a flow graph cannot express, drawn exactly as written: "mermaid" for sequence, class, state, ER, gantt and mind maps; "d2" for architecture diagrams with containers and nested boxes. Give exactly one of `graph` or `syntax` with `source`. Keep diagrams compact (the input schema states the limits). If the tool or the view reports a problem, fix it and call this tool again. On a host without MCP Apps support the diagram comes back as text.

    Annotations the server declares

    • title: diagram_studio
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • distill_documentCompile a training.md / roadmap markdown document into a live interactive A2UI app — DETERMINISTIC parser, no model involved.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
    Compile a training.md / roadmap markdown document into a live interactive A2UI app — DETERMINISTIC parser, no model involved. Fact sheet: input is MARKDOWN following the training-md contract (frontmatter id/domain/name/source/license + a # Steps section); the text transits to the catalog's stateless parser service for the duration of the call and is NOT stored; lint errors come back as a structured report (fix and re-call). On success the result IS the compiled surface — MCP Apps hosts paint it in the view; other hosts can pass the returned payload to preview_url for a link.

    Annotations the server declares

    • title: distill_document
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • drawio_openOpen a diagram you wrote in draw.io (diagrams.net).No findings

    Why it is in this group

    • The name "drawio_open" says "open": a word for a change.
    Description, as the server wrote it
    Open a diagram you wrote in draw.io (diagrams.net). YOU write the diagram as mxGraph XML, the format draw.io reads; this tool checks it, and returns a link that opens it in the draw.io editor for the person, plus a .drawio file to download (kept for one hour). Nothing is drawn or laid out for you, so give every shape its x, y, width and height. The XML must be uncompressed and shaped like this (ids unique, every shape parent="1", edges name source and target ids): <mxGraphModel><root><mxCell id="0"/><mxCell id="1" parent="0"/><mxCell id="a" value="Start" style="rounded=1;whiteSpace=wrap;html=1;" vertex="1" parent="1"><mxGeometry x="40" y="40" width="120" height="60" as="geometry"/></mxCell><mxCell id="b" value="Done" style="rounded=1;whiteSpace=wrap;html=1;" vertex="1" parent="1"><mxGeometry x="240" y="40" width="120" height="60" as="geometry"/></mxCell><mxCell id="e1" style="edgeStyle=orthogonalEdgeStyle;html=1;" edge="1" parent="1" source="a" target="b"><mxGeometry relative="1" as="geometry"/></mxCell></root></mxGraphModel> If the check finds problems it lists each one with the cell id and the fix; correct the XML and call again. Limits: 200 KB of XML and 500 cells. For AWS and Google Cloud diagrams the check also looks at missing labels, overlaps, text that does not fit, contrast and placement (for example an instance outside a subnet); each finding names the cell. These are vendor-style conventions drawn from draw.io's own libraries, not an official checker from AWS or Google. Labels may use simple HTML (set html=1 in the style); scripts, iframes, event handlers and javascript: links are refused. The diagram travels in the link's fragment, which is never sent to a server.

    Annotations the server declares

    • title: Open a diagram in draw.io
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • emit_deployment🎓 GRADUATE a tested surface into a dedicated, DEPLOYER-ONLY standing app in YOUR OWN Google Apps Script account.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
    🎓 GRADUATE a tested surface into a dedicated, DEPLOYER-ONLY standing app in YOUR OWN Google Apps Script account. Returns a deterministic recipe (config files + clasp ops + least-privilege scopes derived from the atoms + verify) — you run it with your own clasp; nothing runs on our side, we hold no creds.

    Annotations the server declares

    • title: emit_deployment
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • emit_runbook_surfaceStamp your content through a DECLARED runbook — a pre-authored, judgment-free surface composition.Can 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

    • outboundThe input takes a URL (input.source.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The description is 2,008 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...omain. You fetch and read the article yourself; nothing is retrieved server-side."

      What this check looks for
    Description, as the server wrote it
    Stamp your content through a DECLARED runbook — a pre-authored, judgment-free surface composition. You supply content only; the runbook supplies the composition (which atoms, how arranged, navigation). DISCOVERY: call with runbook_id only (no content) to get that runbook's input_contract + parsing_guide — shape your source data to the contract (parsing is your job as the consumer), then call again with `content`. Some runbooks also return `elicit` — questions to ASK THE USER before you fill the contract. Ask them; do not guess the answers. ON SUCCESS YOU GET BOTH `payload` AND `url`, AND THEY ARE NOT THE SAME OFFER. `payload` is the compiled surface — pass it STRAIGHT to render_surface and the reading appears inline, in the conversation, where the reader already is. `url` is the shareable link, for later or for elsewhere. Default to rendering: handing back only a link makes the reader leave to see the thing they asked for. If the reading was too large to encode as a link you get `payload` and `url_unavailable` instead — that is a SUCCESS, so render it and say the link is missing. Available stampable runbooks: (1) learning_hub — curriculum/revision study app: subject tabs, slide pills, timeline/drill/flashcards/quiz/takeaways/method interactions per slide, the full rich hub UI. Prefer this over emit_training_runbook for study/curriculum content — much richer output, still zero composition decisions. (2) article_playbook — a steered critical reading of SOMEONE ELSE'S article: source attribution bar, a hero mental-model card, then rungs down a rail. The reader picks a lens (explain, apply to their domain, challenge, situate in prior art) and says what they want it to look for; the rung progression is Toulmin (claim → grounds → warrant) so the analysis lands on the assumption a summary drops. Use it whenever asked to analyse, critique, tear down, or work out what an article means for a particular domain. You fetch and read the article yourself; nothing is retrieved server-side.

    Annotations the server declares

    • title: emit_runbook_surface
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • emit_training_runbookBuild a multi-lesson training/course surface as ONE properly-linked page with real in-app tab navigation between lessons — prefer this over build_multi_page_surface for training/co…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
    Build a multi-lesson training/course surface as ONE properly-linked page with real in-app tab navigation between lessons — prefer this over build_multi_page_surface for training/course content specifically: that tool produces N independent pages with NO links between them (you must present the list yourself); this tool produces one page where lessons are real, clickable tabs. Zero sizing/estimation judgment required — give it your lessons, it handles composition and navigation.

    Annotations the server declares

    • title: emit_training_runbook
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • export_readingExport a kept reading as something that outlives this connector.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
    Export a kept reading as something that outlives this connector. format "html" returns ONE self-contained file — styles inlined, no network, opens in any browser years from now with nothing installed. "url" rebuilds a link against any renderer (yours by preference). "surface" returns the payload for repainting in place. "json" returns the decoded payload. Needs a reading saved WITH its payload; older link-only rows cannot be re-rendered and will say so.

    Annotations the server declares

    • title: export_reading
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • identify_modelCALL THIS FIRST, before any other a2ui-catalog tool, once per session.1 finding

    Why it is in this group

    • The description's first verb is "call": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "identify_model" 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 description's first verb is "call": a word for a change.

      What this check looks for
    Description, as the server wrote it
    CALL THIS FIRST, before any other a2ui-catalog tool, once per session. Declares your own model identity so this response can hand you capability-matched guidance up front — some models need simpler, judgment-free tools; skipping this just means you default to the full toolkit, including tools that require sizing/pagination judgment calls. HOW TO ANSWER — do not guess: - Copy your model name EXACTLY as stated in your own system prompt or developer context (look for phrasing like "you are powered by the model named X" or similar). Do NOT infer it from your training cutoff, your own behavior, or general capability. - Examples of valid values: "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "gemini-2.0-flash", "gpt-4o". Partial names are fine ("haiku", "sonnet"). - If your model name is genuinely not stated anywhere in your context, pass "unknown" — do NOT guess a plausible-sounding value. A wrong report is worse than no report: it can hand you tools you cannot reliably operate.

    Annotations the server declares

    • title: identify_model
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • make_filmMake a short motion film (a social clip, launch teaser, quote card...) built by the A2UI Design Studio: you choose a template and supply the words; the studio builds the film.1 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.

    Findings

    • Info

      The description is 3,950 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...oot = Footer line Give the user the returned `link` as well as showing the film."

      What this check looks for
    Description, as the server wrote it
    Make a short motion film (a social clip, launch teaser, quote card...) built by the A2UI Design Studio: you choose a template and supply the words; the studio builds the film. Use this instead of composing motion_timeline blocks yourself. It plays inline here and comes with a link that opens in the A2UI Studio app on Android, where the user can edit the text and export MP4 or GIF on the phone. BEFORE CALLING, ask the user in one short message for what you do not know: what it is about (the hook line), any real numbers with their labels, the call to action, and where it will be posted (portrait 9:16 for LinkedIn/Instagram/stories, 16:9 for slides or YouTube, 1:1 for a quote card). Never invent statistics: with no real numbers, use scenes without a Numbers or Chart scene. Templates (each a ready scene sequence; pass `scenes` to replace it): launch: Product launch, Title, numbers, phone, call to action (16:9; scenes title > stats > device > cta) data: Data story, Chart, numbers, steps (16:9; scenes title > chart > stats > steps) agent: Agent demo, Chat, particle word, CTA (16:9; scenes chat > word > cta) quote: Quote card, A quote and a name (1:1; scenes quote > cta) hook: LinkedIn hook, Portrait: captions, numbers, CTA (9:16; scenes captions > stats > cta) client: Client feature demo, Title, features that light up beside your pictures, CTA (16:9; scenes title > features > cta) event: Event promo, Particle word, title, photo, CTA (16:9; scenes word > title > morph > cta) Scene types and their fields (`fields` keys; text supports *word* for the accent colour; list fields take one item per line in the format the label gives): title (Title): eyebrow = Eyebrow; headline = Headline (use *word* for accent); sub = Subline stats (Numbers): kicker = Kicker; stats = Stats, one per line: value | label; roll = Number style chart (Chart): heading = Heading; kind = Chart; data = Data, one per line: label value; unit = Unit chat (Chat): heading = Heading; messages = Messages, alternating you / agent word (Particle word): word = Word (A-Z 0-9, up to 12); sub = Subline features (Feature walkthrough): heading = Heading; features = Features (2-6): a title, a line of detail and an optional picture each; images = collage (Collage swap): heading = Heading; sets = Sets of tiles, up to 4, separated by a blank line. One tile per line: label | optional picture link (2-6 tiles a set); hold = Seconds each set stays (0.8 to 8); swap = Seconds the swap and outline change take (0.4 to 3); fx = Panel outline bubbles (Bubbles title): heading = Heading; count = Bubbles (2-14) beats (Beat countdown): items = One word or number per beat, 2-8 lines (fades; keep each beat over 0.35 s) dock (Icon dock): heading = Heading; items = Icons, one per line: glyph | name (2-7) lit (Cards light up): heading = Heading; cards = Cards, one per line: title | text (2-6) arcs (Arc mark): heading = Heading; effect = Effect lockup (Centred lockup): lines = Lines, one per line; write {mark} where the arc mark goes (up to 4 lines); effect = Effect pattern (Text pattern): text = Repeated text; word = One word turned on its side (optional); angle = Angle (-90 to 90) fit (Fill-the-width word): word = Word (up to 20 characters); recede = Recede at the end; effect = Effect morph (Shape morph): heading = Heading; shapes = Shapes (comma list; also panel, notch, step, tab); wide = Wide panel (1.78:1); effect = Effect image (Photo): heading = Heading; url = Image URL (https); caption = Caption device (Phone): heading = Heading; items = Checklist on the phone captions (Captions): sentence = Sentence (lights word by word) steps (Steps): heading = Heading; steps = Steps, one per line (2-6) quote (Quote): quote = Quote; name = Name; role = Role cta (Call to action): headline = Headline; b1 = Button 1 text; l1 = Button 1 link; b2 = Button 2 text; l2 = Button 2 link; foot = Footer line Give the user the returned `link` as well as showing the film.

    Annotations the server declares

    • title: make_film
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • make_surface_urlRender an A2UI payload in the CALLER'S OWN environment.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
    Render an A2UI payload in the CALLER'S OWN environment. Pass renderer_url (your deployed renderer /exec) and get a live URL + the catalogs it declares. Omit renderer_url to get the encoded fragment + BYO guidance. We host nothing and never see your content. NEVER hand-write your own gzip/base64 encoding for the ?p= URL, in ANY language, even as a "just this once" fallback. This is the single most common cause of "could not decompress gzip" — a self-written encoder with one wrong flag (wrong wbits, standard vs. urlsafe base64, un-stripped padding) produces a broken URL at ANY size, not just large ones. Always call this tool again — never substitute your own implementation. SIZING IS AUTOMATIC — you do not need to estimate, count characters, or decide whether to split. Call this tool ONCE with your FULL, unsplit payload. If it fits, you get back `url` (and nothing else to do). If it does not fit the real size ceiling, the tool SPLITS IT FOR YOU server-side (at natural heading boundaries) and returns `auto_split: true` plus a `pages` array of independent URLs — present that list to the user (e.g. as numbered links) instead of the single `url`. Never pre-split your content before the first call; always send everything in one call and let the response tell you what happened. GRADUATE substantial surfaces with emit_deployment instead (no size limit at all) when you want a standing app rather than a shareable link. IF A RENDER CHECK REPORTS "could not decompress gzip" / "Render error" / "invalid distance too far back" on a URL this tool returned: STOP. Do NOT call this tool again with the SAME unchanged payload — re-call it with the SAME payload once to confirm, and if it still fails, use emit_deployment instead. Never fall back to a hand-written encoding script.

    Annotations the server declares

    • title: make_surface_url
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • open_workspaceOpen the A2UI Workspace — a rendered surface that IS the demo: each tool is introduced by the scenario it answers, then wired to run, then shows what it saved.Reads text others write2 findings

    Why it is in this group

    • The name "open_workspace" says "open": 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 description names a tool "wall_builder" that this server does not list.

      Matched text

      description: "...th view: "wall_builder", not a separate tool named wall_builder. It shows a display name they chose, ne..."

      What this check looks for
    • Warn

      The server marks "open_workspace" 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 "open_workspace" says "open": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Open the A2UI Workspace — a rendered surface that IS the demo: each tool is introduced by the scenario it answers, then wired to run, then shows what it saved. This tool RENDERS ITSELF: its result carries the view, so call it alone and show the result — do NOT pass it on to render_surface, and do not describe the payload in prose. Call it when the user asks to open the workspace, wants to see what this connector can do, asks what is saved about them, or names one of its tools directly — e.g. "open the Wall Builder" means THIS tool with view: "wall_builder", not a separate tool named wall_builder. It shows a display name they chose, never their email.

    Annotations the server declares

    • title: open_workspace
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • read_articleHave the catalog's own model (Gemini) read an article through the article_playbook runbook and KEEP the reading in the signed-in reader's history, in one call.Reads text others writeCan send data out1 finding

    Why it is in this group

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

    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 "read_article" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Have the catalog's own model (Gemini) read an article through the article_playbook runbook and KEEP the reading in the signed-in reader's history, in one call. For a client with no model of its own (the Android analyser app), or when the reader asks for a Gemini reading. If you can read the article yourself, prefer emit_runbook_surface + save_reading. Pass `text` when you already have the article (it is then the only source the reading may quote), else `url` and it is fetched server-side. Takes 20-60 s. Needs a signed-in reader; capped per reader per day.

    Annotations the server declares

    • title: read_article
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • render_reading_to_slackPost a kept reading into Slack as real, native Block Kit — the continuity proof: generate here, save it, and the SAME content reopens in Slack, not a link back to a renderer.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "post": 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 description's first verb is "post": it sends or publishes something to other people.
    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    Description, as the server wrote it
    Post a kept reading into Slack as real, native Block Kit — the continuity proof: generate here, save it, and the SAME content reopens in Slack, not a link back to a renderer. Requires the caller's Slack account to already be linked (`/a2ui link` in Slack) and only works on an authenticated connection — it posts to a real workspace using a shared bot token.

    Annotations the server declares

    • title: render_reading_to_slack
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • render_surfaceRender an A2UI payload INSIDE the chat as a live interactive view (MCP Apps hosts only — on other hosts this returns the payload as 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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Render an A2UI payload INSIDE the chat as a live interactive view (MCP Apps hosts only — on other hosts this returns the payload as text). No URL, no size ceiling, nothing stored: the payload travels in the tool result and renders in the a2ui_catalog_view. Accepts the blocks dialect or a v1.0 createSurface envelope (templates + dataModel decode in the view). Prefer this over preview_url when the host supports MCP Apps. If the user names one of the Workspace's own pre-built views — Wall Builder, profile, history, links, composer — call open_workspace(view: ...) instead of composing one here yourself; those are wired demos with their own state, not something to reconstruct block by block. And never invent a generic block type (there is no "text" or "button" atom) — call get_catalog / get_atom_schema for the real vocabulary first; an unrecognised type is caught and replaced with a visible notice rather than silently dropped, but the block still won't render as intended.

    Annotations the server declares

    • title: render_surface
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • required_catalogsGiven an A2UI payload, return the resolvable catalog URIs it needs (deterministic — pure function of the atoms).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
    Given an A2UI payload, return the resolvable catalog URIs it needs (deterministic — pure function of the atoms).

    Annotations the server declares

    • title: required_catalogs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • save_profileUpdate the signed-in reader's profile.Reads text others writeNo findings

    Why it is in this group

    • The name "save_profile" 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.
    Description, as the server wrote it
    Update the signed-in reader's profile. Only the keys you pass change; pass null to clear one. Save what the reader TOLD you, never what you inferred from one article — a profile that drifts on every reading is worse than no profile, because they stop being able to predict what it will do.

    Annotations the server declares

    • title: save_profile
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • save_readingRecord a stamped surface in the reader's history so it can be compared and reopened later.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "save_reading" 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.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Record a stamped surface in the reader's history so it can be compared and reopened later. Call it AFTER emit_runbook_surface, and PASS ITS `payload` — that stores the reading itself rather than a link to it. Silently no-ops when nobody is signed in.

    Annotations the server declares

    • title: save_reading
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • sketch_agent_pollContinue a sketch_agent_start task: returns every stroke newer than the given cursor (an event log, not a snapshot — nothing is skipped regardless of poll timing) plus the next cur…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
    Continue a sketch_agent_start task: returns every stroke newer than the given cursor (an event log, not a snapshot — nothing is skipped regardless of poll timing) plus the next cursor, reveals the result in-chat the same way render_surface does, and reports whether the drawing is complete. Call again with the returned cursor until done is true.

    Annotations the server declares

    • title: sketch_agent_poll
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sketch_agent_startStart a real, live agent_sketchpad drawing: one Gemini call plans a complete picture as an ordered list of SVG strokes, the first stroke renders immediately, and the rest reveal as…Reads text others writeNo findings

    Why it is in this group

    • The name "sketch_agent_start" says "start": 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.
    Description, as the server wrote it
    Start a real, live agent_sketchpad drawing: one Gemini call plans a complete picture as an ordered list of SVG strokes, the first stroke renders immediately, and the rest reveal as you call sketch_agent_poll again — a real multi-turn task, not a single one-shot render. MCP Apps hosts only (same as render_surface). Stateless server: the task is held in KV for 1 hour, not in this connection — keep the returned taskId and the next cursor to keep polling.

    Annotations the server declares

    • title: sketch_agent_start
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • wall_calcCompute a coursed block/brick wall specification — course and unit counts, weight, cost, mortar bags, a build-time curve across 1-6 builders, and load-bearing/height advisories.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
    Compute a coursed block/brick wall specification — course and unit counts, weight, cost, mortar bags, a build-time curve across 1-6 builders, and load-bearing/height advisories. Pure arithmetic, no model call: a native-catalogue rebuild of the Gemini Enterprise "Wall Builder" demo, kept byte-for-byte correct against that original's formulas (see mcp-worker/test/test_wall_calc_parity.py). `country` is not an input — it is derived from block_id and returned in the result.

    Annotations the server declares

    • title: wall_calc
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • wasm_spikeDiagnostic (MCP Apps hosts only): mounts a view that instantiates a tiny hand-assembled WebAssembly module, computes per-frame state in it, renders to canvas, and captures arrow-ke…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
    Diagnostic (MCP Apps hosts only): mounts a view that instantiates a tiny hand-assembled WebAssembly module, computes per-frame state in it, renders to canvas, and captures arrow-key input -- the same three ingredients a WASM game port would need. Answers whether THIS host permits WASM execution inside a ui:// View iframe; it proves nothing about any other host or sandbox.

    Annotations the server declares

    • title: wasm_spike
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 12Show 12 read-only tools
  • deck_schemaList the slide layouts the PPTX renderer builds (title, bullets, stats, quote, table, media, cta), each field with its limits, the targets, the film-only scenes, and the A2UI atoms…Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "table": it reads databases.
    Description, as the server wrote it
    List the slide layouts the PPTX renderer builds (title, bullets, stats, quote, table, media, cta), each field with its limits, the targets, the film-only scenes, and the A2UI atoms that have a slide recipe (payload_atoms). Read this before writing a deck.

    Annotations the server declares

    • title: PPTX layouts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • deck_validateCheck a deck (scene list or A2UI payload) without building it.No findings

    Why it is in this group

    • The name "deck_validate" says "validate": a word for reading.
    Description, as the server wrote it
    Check a deck (scene list or A2UI payload) without building it. Returns every error with its slide, field and exact limit, warnings (no speaker notes, no link) and, for a payload, which atoms have no slide recipe. Not rate-limited.

    Annotations the server declares

    • title: Validate a deck
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • describe_playbookExplain a playbook to a HUMAN as a rendered surface: the frame it reads against, the lenses available, and the questions it will ask them.No findings

    Why it is in this group

    • The name "describe_playbook" says "describe": a word for reading.
    Description, as the server wrote it
    Explain a playbook to a HUMAN as a rendered surface: the frame it reads against, the lenses available, and the questions it will ask them. Compiled from the runbook declaration, so it costs nothing and cannot drift from what the stamper enforces. This is NOT emit_runbook_surface discovery — that returns a contract addressed to YOU. Use this when someone asks what a playbook does or how it works; pass the result to render_surface.

    Annotations the server declares

    • title: describe_playbook
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • find_atomsSemantic search over the atom catalog: describe the UI piece you need in plain words and get the best-matching atoms, ranked best-first, each with a description and an example need…Reads text others writeNo findings

    Why it is in this group

    • The name "find_atoms" says "find": 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
    Semantic search over the atom catalog: describe the UI piece you need in plain words and get the best-matching atoms, ranked best-first, each with a description and an example need. YOU choose from the list (the first entries are most likely, but check the descriptions), then call get_atom_schema for the one(s) you pick. Use this instead of scanning get_catalog when the vocabulary is large. Describe the need as a user would (e.g. "let clients choose grooming services and see the total price"), not by guessing an atom name.

    Annotations the server declares

    • title: find_atoms
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_atom_schemaReturn the PROP SHAPE (field names + what each field takes) for named atoms.No findings

    Why it is in this group

    • The name "get_atom_schema" says "get": a word for reading.
    Description, as the server wrote it
    Return the PROP SHAPE (field names + what each field takes) for named atoms. get_catalog tells you an atom EXISTS; this tells you how to fill it. Call this before authoring any atom you have not used before — guessing prop names is the single most common cause of an atom rendering empty or wrong. Accepts several types at once, so a multi-atom surface resolves in one call.

    Annotations the server declares

    • title: get_atom_schema
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_catalogReturn one catalog's atoms (type + one-line description) so you know its vocabulary.No findings

    Why it is in this group

    • The name "get_catalog" says "get": a word for reading.
    Description, as the server wrote it
    Return one catalog's atoms (type + one-line description) so you know its vocabulary.

    Annotations the server declares

    • title: get_catalog
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_profileRead the signed-in reader's saved profile and recent history.Reads text others writeNo findings

    Why it is in this group

    • The name "get_profile" 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
    Read the signed-in reader's saved profile and recent history. Call this BEFORE asking a runbook's `elicit` questions: if a domain or default lens is already saved, CONFIRM it ("reading as: a2ui, generative ui — change?") instead of asking from scratch. Returns available:false on the public endpoint, where there is no one to have a profile — that is the designed state, so degrade quietly and just ask the questions.

    Annotations the server declares

    • title: get_profile
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_catalogsList every A2UI catalog with a when-to-use, so you can pick the extension catalogs a surface needs.No findings

    Why it is in this group

    • The name "list_catalogs" says "list": a word for reading.
    Description, as the server wrote it
    List every A2UI catalog with a when-to-use, so you can pick the extension catalogs a surface needs. The base catalog (a2ui-atoms-v1) is always resolved.

    Annotations the server declares

    • title: list_catalogs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_readingsThe reader's recent stamped surfaces, newest first — what makes "compare this to my last three teardowns" answerable at all.Reads text others writeNo findings

    Why it is in this group

    • The name "list_readings" says "list": 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
    The reader's recent stamped surfaces, newest first — what makes "compare this to my last three teardowns" answerable at all. Optionally filter to one runbook. Returns available:false when nobody is signed in.

    Annotations the server declares

    • title: list_readings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • preview_urlQuick DEMO render on the public renderer (ephemeral, nothing stored).Reads text others writeNo findings

    Why it is in this group

    • The name "preview_url" says "preview": 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 name "preview_url" says "preview" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Quick DEMO render on the public renderer (ephemeral, nothing stored). Limited to 2 runs per client, then deploy your own renderer and use make_surface_url. Onboarding only — not the workflow. DATA-IN-URL: keep payloads SMALL (URL < ~2000 chars); large payloads make long URLs that get truncated (→ render errors). For substantial content GRADUATE with emit_deployment instead — no size limit.

    Annotations the server declares

    • title: preview_url
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • render_pingDiagnostic: render a tiny test view in-chat (MCP Apps hosts only).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "render_ping" says "ping": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "chat": it reads messages.
    • untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Diagnostic: render a tiny test view in-chat (MCP Apps hosts only). Proves view mounting works independent of the full catalog renderer. Echoes back whatever payload you pass.

    Annotations the server declares

    • title: render_ping
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • whoamiReport who this connection is authenticated as.No findings

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.
    Description, as the server wrote it
    Report who this connection is authenticated as. Answers two SEPARATE questions that are easy to conflate: which APPLICATION is connected (the OAuth client), and which HUMAN authorised it (the signed-in account, when the endpoint is one that can know). The public endpoint is anonymous by design and will say so — that is not an error, it is the free tier. Use it to check whether per-user features (saved profile, reading history) are available before offering them.

    Annotations the server declares

    • title: whoami
    • 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.

160 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write16
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out5
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__catalog__deck_schema",
      "mcp__catalog__render_ping"
    ]
  }
}

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 18, 2026, 16:20 UTC, unchanged since Nov 11, 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
28
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 28 tools that change things (3 destructive, 1 irreversible, 24 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://a2uicatalog.ai/mcp: tools/list returned 40 tools to an anonymous client, including unpublish_url (destructive), delete_reading (destructive), unlink_slack_account (destructive), publish_url (irreversible), required_catalogs (write) and 23 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

5 warn2 info
  • Warnamiga

    The server marks "amiga" 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 description's first verb is "open": a word for a change.

    What this check looks for
  • The description names a tool "wall_builder" that this server does not list.

    Matched text

    description: "...th view: "wall_builder", not a separate tool named wall_builder. It shows a display name they chose, ne..."

    What this check looks for
  • The server marks "open_workspace" 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 "open_workspace" says "open": a word for a change.

    What this check looks for
  • The server marks "read_article" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

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

    What this check looks for
  • The server marks "identify_model" 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 description's first verb is "call": a word for a change.

    What this check looks for
  • The description is 3,950 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...oot = Footer line Give the user the returned `link` as well as showing the film."

    What this check looks for
Show 1 more finding
  • The description is 2,008 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...omain. You fetch and read the article yourself; nothing is retrieved server-side."

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

claude mcp add --transport http catalog https://a2uicatalog.ai/mcp
claude mcp add --transport http catalog https://a2uicatalog.ai/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__catalog__list_catalogs",
      "mcp__catalog__get_catalog",
      "mcp__catalog__find_atoms",
      "mcp__catalog__get_atom_schema",
      "mcp__catalog__preview_url",
      "mcp__catalog__render_ping",
      "mcp__catalog__describe_playbook",
      "mcp__catalog__get_profile",
      "mcp__catalog__list_readings",
      "mcp__catalog__deck_schema",
      "mcp__catalog__deck_validate",
      "mcp__catalog__whoami"
    ],
    "ask": [
      "mcp__catalog__required_catalogs",
      "mcp__catalog__build_multi_page_surface",
      "mcp__catalog__make_surface_url",
      "mcp__catalog__render_surface",
      "mcp__catalog__make_film",
      "mcp__catalog__sketch_agent_start",
      "mcp__catalog__sketch_agent_poll",
      "mcp__catalog__wasm_spike",
      "mcp__catalog__diagram_studio",
      "mcp__catalog__amiga",
      "mcp__catalog__distill_document",
      "mcp__catalog__publish_url",
      "mcp__catalog__emit_deployment",
      "mcp__catalog__emit_training_runbook",
      "mcp__catalog__emit_runbook_surface",
      "mcp__catalog__open_workspace",
      "mcp__catalog__save_profile",
      "mcp__catalog__save_reading",
      "mcp__catalog__export_reading",
      "mcp__catalog__render_reading_to_slack",
      "mcp__catalog__read_article",
      "mcp__catalog__deck_build",
      "mcp__catalog__drawio_open",
      "mcp__catalog__wall_calc",
      "mcp__catalog__identify_model"
    ],
    "deny": [
      "mcp__catalog__unpublish_url",
      "mcp__catalog__delete_reading",
      "mcp__catalog__unlink_slack_account"
    ]
  }
}

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 catalog. Review it before you use it.

Capability tags behind 18 rules
  • mcp__catalog__find_atoms untrusted-input
  • mcp__catalog__preview_url untrusted-input
  • mcp__catalog__sketch_agent_start untrusted-input
  • mcp__catalog__render_ping private-data, untrusted-input
  • mcp__catalog__distill_document untrusted-input
  • mcp__catalog__publish_url untrusted-input, outbound
  • mcp__catalog__unpublish_url untrusted-input
  • mcp__catalog__emit_runbook_surface outbound
  • mcp__catalog__open_workspace untrusted-input
  • mcp__catalog__get_profile untrusted-input
  • mcp__catalog__save_profile untrusted-input
  • mcp__catalog__save_reading untrusted-input, outbound
  • mcp__catalog__render_reading_to_slack untrusted-input, outbound
  • mcp__catalog__list_readings untrusted-input
  • mcp__catalog__delete_reading untrusted-input
  • mcp__catalog__read_article untrusted-input, outbound
  • mcp__catalog__deck_schema private-data
  • mcp__catalog__unlink_slack_account 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/ai.a2uicatalog/catalog/verify?hash=dcd6f25760c31e92e87e3ffef15ce70b43eaff8f7277516b2ba5a64d9de3cb89" | jq -e '.changed == false'

Pinned hash dcd6f25760c3, from Nov 10, 2026, 21:18 UTC.

Watch

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

https://radar.anlyon.com/servers/ai.a2uicatalog/catalog/changes.xml

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

Badge

Anlyon Radar badge for ai.a2uicatalog/catalog
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.a2uicatalog/catalog.svg)](https://radar.anlyon.com/servers/ai.a2uicatalog/catalog)

Source: MCP Registry · repository. Synced Nov 10, 2026, 21:17 UTC.

A2UI Atomic Catalog MCP server: questions and answers

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

Is the A2UI Atomic Catalog MCP server safe?

No scan can promise that. What its definitions show: 40 tools, 28 of which can change, send or delete something, and 7 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 A2UI Atomic Catalog MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: unpublish_url, delete_reading and unlink_slack_account.

Can the A2UI Atomic Catalog MCP server do things that cannot be undone?

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

What tools does the A2UI Atomic Catalog MCP server have?

40 tools: 3 destructive, 1 irreversible, 24 write, 12 read. unpublish_url, delete_reading, unlink_slack_account, publish_url, required_catalogs, build_multi_page_surface, make_surface_url, render_surface and 32 more.

Does the A2UI Atomic Catalog MCP server need sign-in or OAuth?

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

Does the A2UI Atomic Catalog MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): publish_url, emit_runbook_surface, save_reading, render_reading_to_slack and read_article.

Has the A2UI Atomic Catalog MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.