cd /news/ai-agents/show-hn-ojcp-an-open-protocol-for-ag… · home topics ai-agents article
[ARTICLE · art-93861] src=ojcp.dev ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Show HN: OJCP – an open protocol for agent-consumable job data

OJCP, an open protocol for agent-consumable job data built on MCP and interoperable with schema.org, defines how AI agents discover, reason over, and act on job opportunities, with governance by an independent steering committee. The protocol includes seven core schemas and six standard MCP tools, requiring providers to implement search_jobs, and supports consent-first privacy, agent-aware ranking, and WebMCP readiness.

read3 min views1 publishedAug 12, 2026

|

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.

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. Agents self-declare identity.

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.

Specification

Schemas & Tools #

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

).

MCP Tools

Job Manifest Discovery endpoint at /.well-known/ojcp.json

ojcp_version

provider

tools

mcp_endpoint

auth

rate_limits

[JobPosting](https://spec.ojcp.dev/#schema-job-posting)

Extends schema.org/JobPosting with agent-specific fields

ojcp_id

skills_required

experienceLevel

apply_paths

urgency

CandidateContext Consent-scoped candidate profile for personalized results

consent_scope

skills

experience_years

employment_type_preference

AgentDeclaration Agent self-identification for audit trails

agent_id

acting_on_behalf_of

interaction_mode

user_consent_token

VerificationStep Identity verification action for human completion

step_id

type

verifier_id

verification_url

human_required

VerificationProof JWS proof with required claims: iss, aud, sub, iat, exp, nonce — no PII

step_id

verifier_id

`proof_token (JWS)`

`subject_hash (SHA-256)`

issued_at

expires_at

VerifierManifest Discovery document hosted at /.well-known/ojcp-verifier.json

verifier_id

verification_types

proof_delivery_methods

proof_format (jws|jws+jwe) signing_algorithms

public_keys_url (JWKS) 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 v0.1 specification covers tools, schemas, apply paths, and security requirements.

View Specification Explore Schemas

JSON Schemas for JobPosting, CandidateContext, AgentDeclaration, and the Manifest.

Browse Schemas Contribute

OJCP is open. File issues, propose changes, or build a reference implementation.

Open an Issue Join the Discussion

Shape the future of agent-ready hiring. We welcome ATS vendors, job boards, and agent developers.

Get Involved

── more in #ai-agents 4 stories · sorted by recency
── more on @ojcp 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-ojcp-an-open…] indexed:0 read:3min 2026-08-12 ·