LoginStart beta
*Ayneye
MCP quickstartStart beta

MCP for video agents

MCP should expose safe video resources, not uncontrolled camera authority.

Ayneye's MCP direction is a governed interface over durable video artifacts: World-State, timeline, evidence, detector reports, and cost. The public beta uses REST and dashboard first; MCP-style tools remain preview-only until separately audited.

REST-first betaRead-only resourcesEvidence requiredPolicy-gated actions

MCP operating model

MCP is useful when an AI tool needs a consistent way to discover resources, call bounded tools, and cite what it used. For video, that interface must be narrower than raw camera control. Ayneye treats MCP as a bridge from an agent runtime to already-materialized artifacts. The server does not give the model the right to interpret identity, infer intent, unlock doors, trigger dispatch, or perform physical actions.

LayerWhat it exposesWhat it does not expose
Resourcesscene_graph, timeline, evidence_bundle, detector_report, cost artifactsRaw unrestricted camera control
Toolsread_scene, get_evidence, ask_with_evidence, get_cost_contextDestructive or physical actions
Policiesrisk class, review_required, allowed claim types, blocked operationsSilent escalation
Audittool call trace, evidence refs, limits, cost contextOpaque agent behavior

Choose the right MCP path

Current beta boundary

Real signup, dashboard, REST APIs, and artifacts are working evaluation surfaces. MCP is positioned as a preview integration model. Paid checkout, automated email campaigns, CRM writes, and production MCP authority remain disabled until separately enabled and verified.

The purpose of this page is to make the MCP boundary concrete for builders, buyers, and reviewers. A useful MCP integration is not a promise that an agent can watch everything and decide everything. It is a disciplined interface over already-materialized evidence. Each tool call should be tenant-scoped, read-only by default, evidence-aware, cost-aware, and auditable. If the request asks for identity, intent, physical access, emergency response, employment action, or destructive change, the tool returns a review-required state instead of pretending that a video artifact is a final decision. This keeps the product useful for developers while making it credible for security, legal, and operations teams.