OJCP: Open protocol for agent-consumable job data and applications

What it does

OJCP is an open protocol that allows AI agents to discover, evaluate, and apply to job opportunities programmatically. It defines standard schemas and MCP tools—including search_jobs, get_job_detail, and begin_application—that let agents interact with job boards, ATS systems, and employer career pages through a consistent interface. Employers publish a manifest at /.well-known/ojcp.json describing their available tools and capabilities. Agents use this to find providers, retrieve job details with fit scoring, and submit applications without scraping or fighting bot detection.

Who it is for

OJCP targets three groups: AI agent builders who need reliable job application APIs; employers and job boards tired of bot scraping and form-fighting; and ATS vendors and staffing platforms seeking interoperability. The protocol is also relevant to candidates using agent-driven job search, though agents act on their behalf under consent.

Pricing

The site does not show prices.

How it stands out

OJCP is governance-first, with an independent steering committee holding seats from employers, ATS vendors, job boards, staffing agencies, and agent platforms—none holding veto power. This coalition structure shields it from vendor lock-in. The protocol is built on MCP (Model Context Protocol) and interoperable with schema.org, making it composable with the broader agentic web. It emphasizes consent-scoped privacy: candidate data is opt-in, resumes are embedded for fit scoring without transmitting PII, and agents self-declare identity for audit trails. A normalized taxonomy of application mechanisms lets agents know exactly which apply paths are available—ATS-direct, agent-ready, or verification-gated—rather than guessing.

What a founder should check

Someone building a rival or alternative should verify: (1) Whether the steering committee structure actually prevents vendor capture or if one large player will dominate adoption anyway—check who is actively implementing and pushing the spec versus who is just a committee seat; (2) How switching costs for job boards and ATS vendors compare to staying on proprietary APIs—many platforms have zero financial incentive to expose structured data if they already extract value from recruiter friction; (3) The moat: whether agents will fragment across multiple protocols or consolidate on OJCP, and whether the MCP/schema.org foundation is stable enough to avoid obsolescence as agent tech evolves.

Thinking of building something like this?

Every launch here is a competitor to somebody's idea. If yours is close, check it against the market before you build: the Full Check names the rivals, the prices and the gaps.