MCP servers › ai.a2uicatalog › catalog
MCP server · registry snapshot 2026-11-12 · last tested 2026-11-18
catalog MCP server
Registry name ai.a2uicatalog/catalog
A2UI Atomic Catalog — the publisher's title
by a2uicatalog.ai · domain (the registry's namespace rule)repository owner on GitHub: a2uicatalog (personal account)Source ↗Website ↗
500+ typed UI atoms an agent composes into real rendered interfaces. Free, no API key. — the publisher's description
Summary
ai.a2uicatalog/catalog is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain a2uicatalog.ai. Its linked repository is github.com/a2uicatalog/a2ui; GitHub reports its owner as a2uicatalog, a personal account. On 2026-11-18 ProtocolProbe connected to it in read-only mode and read its inventory: 40 tools, 173 resources and 0 prompts.
Record checks
4 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 7 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 40
- Last tested
- 2026-11-18
Tool list size
19,347 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (40 tools). Counted with Anthropic's token counter on 2026-11-18, from the tool list we read on 2026-11-18. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-18 (a2uicatalog.ai), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.0.0).
Observed fact
This server accepted a session without any credential and lists 5 tools whose name or declaration suggests they change data (unpublish_url, save_profile, save_reading, delete_reading, unlink_slack_account). That is our reading of the names; we did not call them. Source: our connection, 2026-11-18.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-18
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-11-10 (registry, as of the 2026-11-12 snapshot)
- First listed version
- 2026-11-10 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-12
- Package and repository
- checked 2026-11-12
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-11-09, listed on 2026-11-12 with version 1.0.0 (published 2026-11-10).
Source: the official MCP Registry list on 2026-11-09 and on 2026-11-12.
What it is
What does this server offer?
Observed inventoryNone of its 40 tools are described as changing anything. For 40 the reading was uncertain, so no mark is shown.
- list_catalogson 1 other server
“List every A2UI catalog with a when-to-use, so you can pick the extension catalogs a surface needs.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- get_catalogon 69 other servers
“Return one catalog's atoms (type + one-line description) so you know its vocabulary.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
catalogstringrequired“catalog slug or catalogId URI”
- 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, each with a description and an example need.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
needstringrequired“The UI piece you need, in plain words (one need per call)”kinteger“How many candidates to return (default 10, max 50).”rendererstring“Optional renderer id: react, lit, angular, copilotkit, a2ui-vue, flutter or compose.”include_degradedboolean“With renderer only: also keep atoms with status degraded (Flutter lowers them to Basic components, so they show but not as the atom intends).”
- get_atom_schema
“Return the PROP SHAPE (field names + what each field takes) for named atoms.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
typesarrayrequired“Atom type names, e.g.”
- required_catalogs
“Given an A2UI payload, return the resolvable catalog URIs it needs (deterministic — pure function of the atoms).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
payloadobjectrequired“The A2UI payload to inspect: {title, theme, blocks:[...]} in the blocks dialect.”
- 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 own independently-encoded page (no shared hub, so per-page si…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
titlestringrequired“Hub page title”sectionsarrayrequired“Array of {heading, content} sections”renderer_urlstring“Your deployed renderer /exec URL (optional; defaults to BYO)”
- make_surface_url
“Render an A2UI payload in the CALLER'S OWN environment.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
payloadobjectrequired“The A2UI payload to encode into a ?p= URL: {title, theme, blocks:[...]}.”renderer_urlstring“your renderer /exec (BYO).”
- preview_urlon 2 other servers
“Quick DEMO render on the public renderer (ephemeral, nothing stored).”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
1 input, 1 required
payloadobjectrequired“The A2UI payload to preview: {title, theme, blocks:[...]}.”
- render_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).”
Publisher declares: read-only yes · destructive no · idempotent no · open-world no
1 input, 1 required
payloadobjectrequired“The A2UI payload to render in the chat view: blocks dialect {title, theme, blocks:[...]} or a v1.0 createSurface envelope.”
- make_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 the words; the studio builds the film.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
templatestringrequired“Starting template.”titlestring“Film title (also the file name when exported).”aspectstring“Override the template aspect.”lookstring“Colour preset.”pacestring“Timing preset for scene length and transitions.”scenesarray“Scenes in order, replacing the template's.”
- sketch_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 renders immediately, and the rest reveal as you call sketch_ag…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
subjectstringrequired“What to draw, e.g.”
- sketch_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 regardless of poll timing) plus the next cursor, reveals the re…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
taskIdstringrequired“The taskId returned by sketch_agent_start.”cursorintegerrequired“The cursor returned by the previous start/poll call.”
Show 28 more tools
- render_ping
“Diagnostic: render a tiny test view in-chat (MCP Apps hosts only).”
Publisher declares: read-only yes · destructive no · idempotent no · open-world no
1 input
payloadobject“Any JSON object; it is echoed back as the result so you can see what the view received.”
- wasm_spike
“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…”
Publisher declares: read-only yes · destructive no · idempotent no · open-world no
Takes no inputs.
- 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).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
graphobject“The diagram as a graph (preferred).”directionstring“Graph layout direction: TB (top to bottom, default) or LR.”formatstring“Which format the view opens on.”themestring“Colours for the draw.io output.”syntaxstring“Only with `source`: the language of that source.”sourcestring“Only with `syntax`: a complete diagram, drawn as written.”titlestring“Optional heading shown above the diagram.”
- amiga
“Open a real, cycle-exact Amiga 500 emulator in-chat (MCP Apps hosts only).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- distill_document
“Compile a training.md / roadmap markdown document into a live interactive A2UI app — DETERMINISTIC parser, no model involved.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs, 1 required
markdownstringrequired“the full markdown document, frontmatter included”domainstring“parse contract to apply (default training)”
- publish_url
“STORES the payload server-side and returns a SHORT shareable link.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 2 required
payloadobjectrequired“The A2UI payload to store and share: {title, theme, blocks:[...]}, up to 100 KB serialised.”acknowledge_storagebooleanrequired“MUST be true — affirms the user consented to server-side storage”targetstring“Where the short link opens: "play" (default) the a2uicatalog playground by reference, "gas" the public Apps Script renderer.”aliasstring“optional vanity name for the link (/s/<alias>) — first-come, frees when the link expires”ttl_daysnumber“OPERATOR-ONLY (authenticated requests): retention override; 0 = permanent.”
- unpublish_url
“Delete a published short link before its TTL using the delete_token returned by publish_url.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
2 inputs, 2 required
idstringrequired“The published link id, or the full short URL (https://a2uicatalog.ai/s/<id>) returned by publish_url.”delete_tokenstringrequired“The delete_token that publish_url returned for this link.”
- emit_deployment
“🎓 GRADUATE a tested surface into a dedicated, DEPLOYER-ONLY standing app in YOUR OWN Google Apps Script account.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
payloadobjectrequired“The tested A2UI payload to bake into the standing app as its home surface: {title, theme, blocks:[...]}.”app_namestring“Name for the Apps Script project and its folder.”
- emit_training_runbook
“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 specif…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
titlestringrequired“Course title”lessonsarrayrequired“Array of {heading, content} lessons — each becomes its own tab”renderer_urlstring“Your deployed renderer /exec URL (optional; defaults to BYO)”
- emit_runbook_surface
“Stamp your content through a DECLARED runbook — a pre-authored, judgment-free surface composition.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
runbook_idstringrequired“Stampable runbook name.”contentobject“Your content shaped to the runbook's input_contract.”sourceobject“The source the USER supplied (workspace surfaces pass this; you normally do not).”renderer_urlstring“Your deployed renderer /exec URL (optional; defaults to the public demo renderer)”
- describe_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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
runbook_idstringrequired“Which stampable runbook to describe.”
- open_workspaceon 2 other servers
“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.”
Publisher declares: read-only yes · destructive no · idempotent no · open-world yes
2 inputs
viewstring“Which screen to open — omit or "home" for the tool selector.”promptstring“Composer view only.”
- get_profileon 174 other servers
“Read the signed-in reader's saved profile and recent history.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
- save_profileon 5 other servers
“Update the signed-in reader's profile.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
5 inputs
domainsarray“Areas of interest the apply lens transfers into, e.g.”default_lensstring“Opening posture when the reader does not name one: explain | apply | challenge | situate.”concernsstring“Standing things they always want pushed on, in their own words.”display_namestring“What to call them in a rendered surface.”themestring“Reader's preferred UI theme.”
- save_reading
“Record a stamped surface in the reader's history so it can be compared and reopened later.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 1 required
runbookstringrequired“e.g.”urlstring“The stamped surface url returned by emit_runbook_surface.”titlestring“The ANALYSIS title (yours), not the source headline.”source_urlstring“The original article, so history stays attributable.”source_titlestring“The original article's headline, kept beside source_url.”lensstring“The lens the reading was made through (e.g.”payloadobject“The compiled surface emit_runbook_surface returned (its `payload`).”
- export_reading
“Export a kept reading as something that outlives this connector.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
idstring“Reading id from list_readings.”formatstring“Default html.”renderer_urlstring“For format "url": your own renderer /exec.”
- 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 Slack, not a link back to a renderer.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
idstring“Reading id from list_readings.”channelstring“Slack channel to post to.”
- list_readingson 8 other servers
“The reader's recent stamped surfaces, newest first — what makes "compare this to my last three teardowns" answerable at all.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
runbookstring“Filter to one runbook, e.g.”limitinteger“Default 20, max 100.”
- delete_reading
“Permanently remove one or more of the reader's saved readings from their History.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
idsarrayrequired“Reading ids from list_readings.”
- read_articleon 7 other servers
“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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs, 1 required
urlstringrequired“The article's public URL.”textstring“The article text, if the caller already fetched it.”source_titlestring“The article's headline, kept with the reading for attribution.”lensstring“Default explain.”domainsstring“For lens "apply": the reader's domains, comma-separated.”concernsstring“What the reader wants the reading to look for or push back on.”
- deck_schema
“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 …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- deck_validate
“Check a deck (scene list or A2UI payload) without building it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
deck“A typed scene list: {"title","target","scenes":[{"type":"title|bullets|stats|quote|table|media|cta","f":{...fields...},"notes":"speaker notes"}]}.”payload“An A2UI payload {"blocks":[{"type":"quote",...},...]}: each atom with a slide recipe becomes slides, others are listed under `unsupported`, never guessed.”skip_film_onlyboolean“For a scene list that came from a film: leave out scenes with no slide layout (chart, chat, word, morph, captions, image) instead of treating them as errors.”
- deck_build
“Build a PowerPoint (.pptx) file from a scene list or an A2UI payload.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
5 inputs
deck“A typed scene list: {"title","target","scenes":[{"type":"title|bullets|stats|quote|table|media|cta","f":{...fields...},"notes":"speaker notes"}]}.”payload“An A2UI payload {"blocks":[{"type":"quote",...},...]}: each atom with a slide recipe becomes slides, others are listed under `unsupported`, never guessed.”targetstring“Where the file will be opened.”deliverystring“How the .pptx comes back.”skip_film_onlyboolean“For a scene list that came from a film: leave out scenes with no slide layout (chart, chat, word, morph, captions, image) instead of treating them as errors.”
- drawio_open
“Open a diagram you wrote in draw.io (diagrams.net).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
7 inputs, 1 required
xmlstringrequired“The mxGraph XML: an <mxGraphModel> (or an uncompressed <mxfile> holding one).”titlestring“Optional name for the downloaded file, for example "checkout-flow".”stylestring“Style pack.”restyleboolean“Rewrite recognised services to draw.io's own icon styles and recognised groups (AWS: VPC, subnets, Region; Google Cloud: zones) to their group styles.”polishstring“Visual finish using draw.io's own effects, layered on your styles without overriding any key you set: clean (default, nothing added), soft (rounded corners, ge…”animateboolean“Add moving dashes along the connectors (draw.io flow animation).”hoststring“diagrams (default): open in app.diagrams.net.”
- unlink_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` command — see slack-compiler/DESIGN-identity.md, "many Slack -> o…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
keysarrayrequired“slack_key values from the Links view, "{team_id}:{user_id}".”
- wall_calc
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs, 4 required
block_idstringrequired“parpaing200/150 and brique are French standards; uk_brick/uk_block are UK standards.”height_mnumberrequired“0.2-20m, snapped to 0.2m steps.”width_mnumberrequired“0.2-20m, snapped to 0.2m steps.”patternstringrequired“running = half-unit stagger on alternate courses; stack = none.”load_bearingboolean“Triggers an advisory (not a block swap) if the chosen block is under the load-bearing weight threshold.”include_dpcboolean“Adds a damp-proof-course length to the result.”buildersnumber“1-6, snapped/clamped.”
- whoamion 208 other servers
“Report who this connection is authenticated as.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- identify_model
“CALL THIS FIRST, before any other a2ui-catalog tool, once per session.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
modelstringrequired“Your own model identifier, exactly as your system prompt states it, or "unknown" if not stated.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-18.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 100% of 102
- Tools with a description
- 100% of 40
- Typical description length
- 639 characters
The tool set
Counted from the listing
- Tools
- 40
- Size of the list
- about 19,306 tokens for an agent to load (characters ÷ 4)
- Naming
- 38 of 40 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 40 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-18 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://a2uicatalog.ai/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"catalog": {
"url": "https://a2uicatalog.ai/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"catalog": {
"type": "http",
"url": "https://a2uicatalog.ai/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"catalog","type":"http","url":"https://a2uicatalog.ai/mcp"}'Claude Code
claude mcp add --transport http catalog https://a2uicatalog.ai/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"catalog": {
"type": "streamableHttp",
"url": "https://a2uicatalog.ai/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"catalog": {
"httpUrl": "https://a2uicatalog.ai/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.catalog] url = "https://a2uicatalog.ai/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"catalog": {
"url": "https://a2uicatalog.ai/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://a2uicatalog.ai/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-12. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-12. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-12. Source: read 2026-11-12.
- Cline marketplace. Not in the Cline marketplace on 2026-11-12. Source: read 2026-11-12.
Own host
- security.txt. No security.txt at https://a2uicatalog.ai/.well-known/ (HTTP 404, 2026-11-12). Source: a2uicatalog.ai/.well-known/security.txt · read 2026-11-12.
- A2A agent card. An A2A agent card is published at https://a2uicatalog.ai/.well-known/agent-card.json (name, skills, url). Source: a2uicatalog.ai/.well-known/agent-card.json · read 2026-11-12.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint a2uicatalog.ai/mcp | Session opened | matches | our test · 2026-11-18 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-18 |
| Repository github.com/a2uicatalog/a2ui | Opens publicly | matches | api.github.com · 2026-11-12 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- ai.a2uicatalog · 2 servers
- GitHub owner
- a personal account (a2uicatalog)
- Repository
- github.com/a2uicatalog/a2ui
- Stars
- 7
- Repository age
- 91–180 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-11-12; security policy read from GitHub · 2026-11-12.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Tool list changes
Our reads compared · no tool calledHosted endpoint a2uicatalog.ai/mcp
1 of 1 comparison between consecutive reads showed a change (2 reads, 2026-11-12 to 2026-11-18; version 1.0.0).
Last change seen between our reads on 2026-11-12 (version 1.0.0) and 2026-11-18 (version 1.0.0). Changed without a new version: both reads list version 1.0.0.
Changed (2):
find_atoms: description, input schemaget_atom_schema: descriptionCompared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-18 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating4 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 7 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-12 (security policy 2026-11-12). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about ai.a2uicatalog/catalog
Answered from the data aboveWho publishes ai.a2uicatalog/catalog?
The registry ties the namespace ai.a2uicatalog to the domain a2uicatalog.ai; only its owner can publish under it. Its linked repository is github.com/a2uicatalog/a2ui; GitHub reports its owner as a2uicatalog, a personal account. These are facts from the registry and GitHub, not a rating.
Is ai.a2uicatalog/catalog safe to install?
We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does ai.a2uicatalog/catalog need an API key or sign-in?
It opened a session without any credential on 2026-11-18. The registry entry declares no required credential; no declaration is not a guarantee.
Has ai.a2uicatalog/catalog been security tested?
Partly. 4 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Does ai.a2uicatalog/catalog publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Where is the source code of ai.a2uicatalog/catalog?
In github.com/a2uicatalog/a2ui, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
4 exercised11 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-18, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 108 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 40 tools, 173 resources, 0 prompts.
- 74,821 msFinished: 4 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “ai.a2uicatalog/catalog: MCP server record.” Data checked 2026-11-18. https://protocolprobe.com/mcp/servers/ai.a2uicatalog/catalog
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/ai.a2uicatalog/catalog)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology