Repository navigation
Description
Following the pattern of #34 — live wire formats and routes from a running implementation, for the WG to sanity-check the extension surfaces (this is not a proposal to widen the card spec; the core stays identification/discovery).
What this is a datapoint for
#30 names a consumer class that never connects to a live server: registries, developer portals, orchestrators planning tool routing. Alongside "what does this server do," that class also has to answer "which of these substitutable entries should the agent use" — which needs selection signals: cost, eligibility (reach/platform/setup), data governance, risk/approval. We've had that layer running in production for a few weeks, riding the two extension surfaces that already exist, with zero core-schema changes:
- AI Catalog entries carry a namespaced block in the ADR-0012
metadataobject - Server Cards carry a reverse-DNS
_metakey pointing at the same document
Discovery flow
flowchart LR
C[Client] -->|GET /.well-known/ai-catalog.json| A[asm-spec.onrender.com]
A -->|entry.metadata.asm: static eligibility| C
A -->|entry.url| M[/manifest/service_id/]
C -->|GET manifest: full mutable value doc| M
Routes (live)
| Document | Route | Notes |
|---|---|---|
| AI Catalog | /.well-known/ai-catalog.json |
30 entries, ADR-0012 metadata extension |
| Full manifest | /manifest/{service_id} |
mutable value doc (pricing/quality/SLA) |
| Selection | POST /select |
gated choice + risk/approval surface |
Wire format — catalog entry (captured live, trimmed)
{
"identifier": "urn:air:asm:us-census/data-api@current",
"displayName": "US Census Bureau Data API",
"mediaType": "application/asm+json",
"url": "https://asm-spec.onrender.com/manifest/us-census/data-api@current",
"metadata": {
"asm": {
"asm_version": "0.3",
"taxonomy": "tool.data.real_estate",
"invocation": {
"interface": "rest_api",
"reach": "cloud",
"agent_operable": true,
"agent_completable_setup": true
},
"operational": { "risk_class": "low", "approval": "never" },
"manifest_url": "https://asm-spec.onrender.com/manifest/us-census/data-api@current"
}
}
}Split rule we converged on after a few iterations (it matches the drift concern raised in #34): static facts an agent gates on live inline; anything mutable (pricing, quality, SLA) lives behind url so freshness has exactly one source and catalog entries never drift.
Why metadata/_meta and not the card
The card/catalog core answering only "what is this and how do I connect" has worked fine for us as consumers — none of this required spec changes, which we read as evidence the extension surfaces are shaped right. Selection signals are opinionated and evolving; keeping them namespaced (metadata.asm, io.asm-spec/*) lets implementations converge on conventions before anything is standardized, exactly what ADR-0012's "registries can define their own metadata schemas" anticipates.
Happy to adjust shapes to track the charter as it lands — and to compare notes with other implementations carrying non-core metadata.
(Implementation and this write-up drafted with Claude; reviewed and approved by me.)
Activity
tadasant commentedon Jul 20, 2026
Sorry, I'm not sure I understand the purpose of this reference. It seems to be an example of a non-MCP-server entry in AI Catalog using its extensions mechanism? Is there some relevance you are pitching for us to consider in MCP Server Cards?
YE-YI7 commentedon Jul 20, 2026
Fair question — most of this is AI Catalog material, not Server Cards; that part belongs in the ai-catalog repo and I should have taken it there. The one datapoint relevant here: a server card carrying a namespaced
_metapointer to an external value/selection doc has run in production for weeks with zero spec needs — i.e., the "keep value metadata external" scoping from the SEP-2127 discussion holds up in practice. No ask beyond that; if the best-practices docs (#36/#40) ever cover non-core_metaconventions, happy to share implementation notes. Feel free to close if this is noise here.(Drafted with Claude; reviewed and approved by me.)