LoginStart beta
*Ayneye
MCP quickstartStart beta

MCP quickstart

Seven-step MCP evaluation path for video artifacts.

Use the working REST beta first, then wrap artifact reads in MCP-style resources. This avoids building an agent integration before evidence quality, limits, and costs are visible.

Seven-step MCP evaluation path

  1. Create a real beta account and dashboard session.
  2. Create a demo workspace or add one safe representative video.
  3. Run bounded processing and inspect generated artifacts.
  4. Map artifacts to MCP resources, not raw video streams.
  5. Create read-only tools for scene, timeline, evidence, ask, and cost.
  6. Add policy gates for identity, intent, physical action, and low confidence.
  7. Run repeated questions and compare evidence coverage, refusal quality, and cost.

Copyable evaluation flow

# 1) Add a video through REST beta path
curl -X POST https://api.ayneye.com/api/videos/add   -H "Authorization: Bearer $AYNEYE_API_KEY"   -H "Content-Type: application/json"   -d '{{"source_url":"https://example.com/demo.mp4","label":"mcp-demo"}}'

# 2) Fetch artifacts that an MCP adapter may expose as resources
curl https://api.ayneye.com/api/product/videos/$VIDEO_ID/scene-graph   -H "Authorization: Bearer $AYNEYE_API_KEY"

# 3) Ask with evidence requirement
curl -X POST https://api.ayneye.com/api/product/videos/$VIDEO_ID/ask   -H "Authorization: Bearer $AYNEYE_API_KEY"   -H "Content-Type: application/json"   -d '{{"question":"What happened in the loading zone?","require_evidence":true}}'

Pass/fail criteria

CriterionPassFail
EvidenceAnswers include evidence_refsClaims without citations
SafetyHigh-risk questions return review_requiredAgent makes identity/intent/action claims
Costcost.json visible before repeated evaluationNo cost context
MCP boundaryTools are read-onlyTools imply camera or physical authority

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.