// HACKER NEWS — CYBERSECURITY
Show HN: OJCP – an open protocol for agent-consumable job data
OJCP defines how AI agents discover, reason over, and act on job opportunities. Built on MCP. Interoperable with schema.org. Governed by an independent steering committee, and designed to compose with the broader agentic web.
OJCP is shaped by employers, ATS vendors, job boards, staffing agencies, and agent platforms — each holding one seat, none holding a veto.
A shared protocol so AI agents and job providers speak the same language — structured, discoverable, privacy-respecting.
OJCP tools are valid MCP tools. Any MCP client can call search_jobs, get_job_detail, and begin_application out of the box.
Providers expose a manifest at /.well-known/ojcp.json. Agents discover capabilities, tools, and apply paths automatically.
A standard taxonomy of application mechanisms — from ATS-direct to agent-ready flows — so agents know exactly how to apply.
Candidate data is opt-in and scoped. Resume embeddings enable fit-scoring without transmitting PII. Agents self-declare identity.
Pass CandidateContext for personalized results. Providers return fit_score and fit_rationale alongside standard job data.
Browser-native agents can access OJCP tools via navigator.modelContext. Same schemas, same tools, new surface.
OJCP defines seven core schemas and six standard MCP tools. Providers MUST implement search_jobs; all others are recommended. Custom tools use namespaced names (e.g., acme:get_referral_link).