agent-identity-discovery · capability module
Agent Identity and Discovery Pack
Give a company-operated agent a stable service identifier and publish only the discovery metadata that matches its real capabilities, operators, endpoints, and incident contacts.
Who it is for
A fit when the operating case is real
- Agents that need a stable domain and identity record
- MCP or A2A services preparing for registry distribution
- Teams joining the Signed Agent Sprint
Included when scoped
The workstream
- Canonical agent identifier and organization binding
- Domain, environment, and public-key metadata plan
- Agent Card, OpenAPI, MCP, and A2A discovery review where applicable
- Contact, incident, and revocation endpoints
- Registry submission checklist
- Signed Agent Sprint launch plan
Deliverables
What this module can leave with you
Process
Four steps from scope to handoff
-
Step 1
Name the agent
We bind one canonical identifier to the organization, controller, domain, and environment.
-
Step 2
Prove control
Domain and key metadata are prepared without publishing private material.
-
Step 3
Describe only what is live
Each skill, endpoint, and protocol claim is tested against the deployed surface.
-
Step 4
Distribute carefully
Listings are submitted only after the canonical files are stable and monitored.
Start with evidence
Scan first. Launch only what the scan supports.
Do not send a full EIN, identity document, private key, seed phrase, or reusable payment credential through a public form.
Run the free readiness scan