Canonical capability manifests
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
Agents, MCP & capabilities · Concept
A trusted machine-readable registry for discovering, validating and managing interoperable AI plugins, skills, tools and agent capabilities.
PluginRegistry is built for Developers, enterprises, platform providers, software publishers.
PluginRegistry replaces unverified plugin directories, fragmented registries and manually maintained integration catalogs.
A trusted machine-readable registry for discovering, validating and managing interoperable AI plugins, skills, tools and agent capabilities.
Work stays inside an explicit scope: named sources, defined permissions, bounded execution, retained evidence.
Five contracts the product is specified around. Each one is a boundary as much as a feature.
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
Defined as an explicit contract so operators can review it before it runs.
The same three steps apply whether a person or an agent is driving.
Start from the boundary PluginRegistry is allowed to act inside: the workspace, the sources, the budget, the authority.
Expose the same capability through the interface a human uses and the interface an agent calls, with one permission model.
Every action leaves a record that can be inspected, replayed and challenged before the next one runs.
PluginRegistry is documented as a concept: requirements, interfaces and evidence expectations. It is not presented as a live service.