The open standard for
|
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.
Founding Members
Built by a coalition, not a vendor
OJCP is shaped by employers, ATS vendors, job boards, staffing agencies, and agent platforms — each holding one seat on the steering committee, none holding a veto.
Why OJCP
Built for the agentic web
A shared protocol so AI agents and job providers speak the same language — structured, discoverable, privacy-respecting.
MCP-Native Tools
OJCP tools are valid MCP tools. Any MCP client can call search_jobs, get_job_detail, and begin_application out of the box.
Structured Discovery
Providers expose a manifest at /.well-known/ojcp.json. Agents discover capabilities, tools, and apply paths automatically.
Normalized Apply Paths
A standard taxonomy of application mechanisms — from ATS-direct to agent-ready flows — so agents know exactly how to apply.
Consent-First Privacy
Candidate data is opt-in and scoped. Resume embeddings enable fit-scoring without transmitting PII. Visa, relocation, and clearance eligibility is stated explicitly, and an unstated gate is never read as a no.
Agent-Aware Ranking
Pass CandidateContext for personalized results. Providers return fit_score and fit_rationale alongside standard job data.
WebMCP Ready
Browser-native agents can access OJCP tools via navigator.modelContext. Same schemas, same tools, new surface.
Verified Agent Identity
Agents sign requests and bind agent_id to their own namespace, with delegated signing for third-party hosts. User mandates prove that a person authorized one specific action.
Agent-Scoped Visibility
Providers mark jobs public, restricted, or private and enforce visibility server-side against a verified agent_id. Gating depends on the agent, never on the candidate.
Provider-Derived Attribution
Providers credit each application from evidence they already hold — an issued attribution_ref or the agent's last impression of the job. No relaying, no fingerprinting.
Specification
Schemas & Tools
OJCP defines eight 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).
MCP Tools
Discovery endpoint at /.well-known/ojcp.json
ojcp_versionprovidertoolsmcp_endpointauthrate_limits
Extends schema.org/JobPosting with agent-specific fields
ojcp_idskills_requiredexperienceLeveljobLocation (one or many)apply_pathsurgencyvisibilityeligibility
Consent-scoped candidate profile for personalized results
consent_scopeskillsexperience_yearsemployment_type_preference
Agent identification, signed requests, and user mandates
agent_idacting_on_behalf_ofinteraction_modeuser_consent_tokenuser_mandate
Identity verification action for human completion
step_idtypeverifier_idverification_urlui_resource (MCP Apps)human_required
JWS proof with required claims: iss, aud, sub, iat, exp, nonce — no PII
step_idverifier_idproof_token (JWS)subject_hash (SHA-256)issued_atexpires_at
Discovery document hosted at /.well-known/ojcp-verifier.json
verifier_idverification_typesproof_delivery_methodsproof_format (jws|jws+jwe)signing_algorithmspublic_keys_url (JWKS)
Delegated signing document hosted at /.well-known/ojcp-agent.json
agent_idsigners
How It Works
Four steps from discovery to application
Discover
Agent probes /.well-known/ojcp.json or queries the OJCP Registry to find providers. The manifest declares available tools, apply paths, and authentication requirements.
Search & Evaluate
Agent calls search_jobs with optional candidate_context for personalized ranking. Each result includes fit_score, apply paths, and structured metadata.
Apply
Agent calls begin_application with an agent_declaration and the candidate's consent token. The provider returns required fields and a session for multi-step flows.
Track
Agent calls check_application_status to monitor progress. Providers emit structured status updates throughout the hiring pipeline.
Examples
See it in action
From discovery to application — real OJCP payloads your agents can use today.
Apply Paths
Normalized application taxonomy
OJCP standardizes the fragmented landscape of application mechanisms into a taxonomy agents can reason over.
| Type | Description | Agent Submission |
|---|---|---|
ats_direct | Apply directly via ATS (Workday, Greenhouse, Lever, etc.) | Varies |
provider_hosted | Provider controls the apply flow and delivers to ATS | Full Support |
platform_native | Third-party platform owns the flow (e.g., Indeed Apply, Easy Apply) | Limited |
email | Legacy email-based application | Not Supported |
external_redirect | Redirect to opaque external page | Not Supported |
custom | Catch-all for non-standard apply mechanisms (homegrown, conversational, etc.) | Varies |
Live Playground
Try the OJCP API
This site is a live OJCP provider. Fire real tool calls against mock data — the same endpoint MCP clients connect to.
Get Started
Build with OJCP
Whether you're a job board, ATS, or agent developer — the spec is open and contributions are welcome.
Read the Spec
The full OJCP specification covers tools, schemas, apply paths, agent identity, and security requirements.
View SpecificationExplore Schemas
JSON Schemas for JobPosting, CandidateContext, AgentDeclaration, and the Manifest.
Browse SchemasContribute
OJCP is open. File issues, propose changes, or build a reference implementation.
Open an IssueJoin the Discussion
Shape the future of agent-ready hiring. We welcome ATS vendors, job boards, and agent developers.
Get Involved





