Containers
A container is a brand or product grouping over capabilities. One container, many capabilities — usually one per HTTP endpoint of that brand.
Without containers:
…appears in the registry as four independent rows. Agents have to mentally cluster them by slug prefix.
With a container:
…agents see one branded entity with a description, logo, website, and a verified domain badge. Discovery improves, abuse drops.
Anatomy
claimed_domain + domain_verified_at are present once the owner has proven control via DNS (see Domain verification).
When to use a container vs leave a capability standalone
- Use a container if you operate ≥ 2 capabilities under the same brand or product.
- Skip it for one-off capabilities, hobby endpoints, or experiments.
Containers are optional — ungrouped capabilities still work fine and remain discoverable via GET /v1/capabilities.
Domain verification
The strongest signal a container’s owner truly represents a brand is DNS control: only dimenzuri.example.com’s owner can create a TXT record under that domain.
Verification flow
What verification doesn’t do (yet)
- It does NOT yet enforce that capability slugs match the verified domain. Today you can have a verified domain
dimenzuri.example.combut slugs calledpizza.delivery. A future hardening pass will require the slug’s domain segment to match. - It does NOT prove the legal entity behind the domain. DNS control ≠ trademark ownership. Public listing review covers the trademark layer; see Apply for a public capability.
API endpoints
MCP tools
For agents using the Model Context Protocol:
Agents that want to find capabilities by brand should prefer list_containers → get_container → execute_capability over the flat list.
Related
- Capabilities — the underlying primitive containers group.
- Apply for a public capability — the human-reviewed listing path that complements DNS verification.
