Typed UI vocabulary for AI agents using the a2ui protocol — 474 atoms an agent
Typed UI vocabulary for AI agents using the a2ui protocol — 474 atoms an agent composes into real rendered interfaces across web, Google Meet, Apps Script, Google Chat and MCP Apps. MCP server, no signup.
active Production-safe Score 93/100 http no auth
At a glance
| Endpoint | https://a2uicatalog.ai/mcp |
|---|---|
| Source | https://github.com/a2uicatalog/a2ui |
| Transport | http |
| Tools | 40 |
| Auth | none |
| First seen | 2026-07-31 20:04:50 |
| Last checked | 2026-11-17 21:48:27 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 469 / 864 ms |
| Last successful check | 2026-11-17 21:48:27 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (40)
list_catalogs— 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 alwaget_catalog— Return one catalog's atoms (type + one-line description) so you know its vocabulary.find_atoms— Semantic search over the atom catalog: describe the UI piece you need in plain words and get the best-matching atoms, ranked best-first, eacget_atom_schema— 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 filrequired_catalogs— Given an A2UI payload, return the resolvable catalog URIs it needs (deterministic — pure function of the atoms).build_multi_page_surface— Build a multi-section A2UI app from raw title+content sections — you never estimate size or decide how to split; each section becomes its owmake_surface_url— Render an A2UI payload in the CALLER'S OWN environment. Pass renderer_url (your deployed renderer /exec) and get a live URL + the catalogs ipreview_url— Quick DEMO render on the public renderer (ephemeral, nothing stored). Limited to 2 runs per client, then deploy your own renderer and use marender_surface— 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). Nmake_film— Make a short motion film (a social clip, launch teaser, quote card...) built by the A2UI Design Studio: you choose a template and supply thesketch_agent_start— Start a real, live agent_sketchpad drawing: one Gemini call plans a complete picture as an ordered list of SVG strokes, the first stroke rensketch_agent_poll— Continue a sketch_agent_start task: returns every stroke newer than the given cursor (an event log, not a snapshot — nothing is skipped regarender_ping— Diagnostic: render a tiny test view in-chat (MCP Apps hosts only). Proves view mounting works independent of the full catalog renderer. Echowasm_spike— Diagnostic (MCP Apps hosts only): mounts a view that instantiates a tiny hand-assembled WebAssembly module, computes per-frame state in it,diagram_studio— Draw a diagram in-chat with the full Diagram Studio interface (MCP Apps hosts only; it opens fullscreen where the host allows it). YOU writeamiga— Open a real, cycle-exact Amiga 500 emulator in-chat (MCP Apps hosts only). Boots straight into AROS, a free open-source environment (no copydistill_document— Compile a training.md / roadmap markdown document into a live interactive A2UI app — DETERMINISTIC parser, no model involved. Fact sheet: inpublish_url— STORES the payload server-side and returns a SHORT shareable link. Opt-in only: requires acknowledge_storage=true — confirm with the user fiunpublish_url— Delete a published short link before its TTL using the delete_token returned by publish_url.emit_deployment— 🎓 GRADUATE a tested surface into a dedicated, DEPLOYER-ONLY standing app in YOUR OWN Google Apps Script account. Returns a deterministic reemit_training_runbook— Build a multi-lesson training/course surface as ONE properly-linked page with real in-app tab navigation between lessons — prefer this overemit_runbook_surface— Stamp your content through a DECLARED runbook — a pre-authored, judgment-free surface composition. You supply content only; the runbook suppdescribe_playbook— 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. Copen_workspace— 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 sget_profile— Read the signed-in reader's saved profile and recent history. Call this BEFORE asking a runbook's `elicit` questions: if a domain or defaultsave_profile— 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 yousave_reading— 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 ITSexport_reading— Export a kept reading as something that outlives this connector. format "html" returns ONE self-contained file — styles inlined, no network,render_reading_to_slack— Post a kept reading into Slack as real, native Block Kit — the continuity proof: generate here, save it, and the SAME content reopens in Slalist_readings— The reader's recent stamped surfaces, newest first — what makes "compare this to my last three teardowns" answerable at all. Optionally filtdelete_reading— Permanently remove one or more of the reader's saved readings from their History. Takes an array so the Workspace's multi-select can deleteread_article— 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 hideck_schema— List the slide layouts the PPTX renderer builds (title, bullets, stats, quote, table, media, cta), each field with its limits, the targets,deck_validate— Check a deck (scene list or A2UI payload) without building it. Returns every error with its slide, field and exact limit, warnings (no speakdeck_build— Build a PowerPoint (.pptx) file from a scene list or an A2UI payload. Deterministic (same input, same bytes), nothing is stored or fetched,drawio_open— 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, andunlink_slack_account— Revoke one or more Slack accounts' link to this reader's store, from the Workspace side (the reverse of the Slack-side `/a2ui unlink` commanwall_calc— Compute a coursed block/brick wall specification — course and unit counts, weight, cost, mortar bags, a build-time curve across 1-6 builderswhoami— Report who this connection is authenticated as. Answers two SEPARATE questions that are easy to conflate: which APPLICATION is connected (thidentify_model— CALL THIS FIRST, before any other a2ui-catalog tool, once per session. Declares your own model identity so this response can hand you capabi
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:48:27 | ✓ | ✓ | 547 ms | 90 | active |
| 2026-11-17 21:33:21 | ✓ | ✓ | 879 ms | 90 | active |
| 2026-11-17 21:18:13 | ✓ | ✓ | 461 ms | 90 | active |
| 2026-11-17 21:03:09 | ✓ | ✓ | 654 ms | 90 | active |
| 2026-11-17 20:47:48 | ✓ | ✓ | 412 ms | 90 | active |
| 2026-11-17 20:32:42 | ✓ | ✓ | 510 ms | 90 | active |
| 2026-11-17 20:17:39 | ✓ | ✓ | 419 ms | 90 | active |
| 2026-11-17 20:02:05 | ✓ | ✓ | 674 ms | 90 | active |
| 2026-11-17 19:46:44 | ✓ | ✓ | 940 ms | 90 | active |
| 2026-11-17 19:31:40 | ✓ | ✓ | 1204 ms | 87 | active |
| 2026-11-17 19:16:33 | ✓ | ✓ | 499 ms | 90 | active |
| 2026-11-17 19:00:53 | ✓ | ✓ | 553 ms | 90 | active |
| 2026-11-17 18:45:51 | ✓ | ✓ | 310 ms | 90 | active |
| 2026-11-17 18:30:49 | ✓ | ✓ | 649 ms | 90 | active |
| 2026-11-17 18:15:46 | ✓ | ✓ | 629 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://a2uicatalog.ai/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/a2uicatalog-ai-mcp # JSON