Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Job Opportunities API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fjobopportunitiesapi.org%2Fjobopportunitiesapi" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fjobopportunitiesapi.org%2Fjobopportunitiesapi" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Job Opportunities API.
Search live job listings with filters such as country, city, remote, seniority, min_salary, posted_after, and a free-text q, paging with a keyset cursor
Return only listings whose remote status the source actually stated with remote_confirmed=true, using each job's field_sources provenance
List roles that have closed at their source, filtered by closed_after, closed_before, and closed_reason
Follow a delta feed of created, updated, withdrawn, and delisted listings since a given point
GET STARTED
Look up employers by country, org_type, or name and read one employer by its slug
Stream the full listing corpus as NDJSON or queue a whole-country export pack and poll its status
Check your key's plan, quota, and daily usage
Patterns agents use Job Opportunities API for, with concrete tasks.
★ Agent Job Search via Jentic
An AI agent helping a candidate searches the Job Opportunities API for live listings matching their country, seniority, and salary floor, then reads each shortlisted listing for its full description. Through Jentic the agent finds the listing search by intent and calls it with your stored bearer token, and because each job carries field_sources it can tell the candidate which details the employer stated and which were inferred.
Search live listings with country 'DE', remote_confirmed=true, and min_salary 70000 for the title 'backend engineer', then fetch the top three by id and summarise each role
Hiring Signal Tracking from Closed Roles
Recruiting analysts and sales teams read the closed roles listing, filtered by closed_after and closed_reason, to see which requisitions came off their source and when. A role that opened and closed quickly is a hiring signal, and pairing it with an employer lookup by slug gives the company context behind the change.
List roles closed after 2026-10-01, group them by company, and look up the three companies with the most closures by their slug
Keeping a Job Board in Sync
A job board or aggregator seeds its database from the NDJSON export, then polls the delta feed with since to apply created, updated, withdrawn, and delisted rows in change order. The expired endpoint returns the ids of roles that have come off the ledger so stale listings can be removed.
Pull the change feed since the last saved checkpoint for country 'GB', apply each created or updated row, and delete the ids returned by the expired endpoint
20 endpoints — the job opportunities api returns employer-direct job listings drawn from employer ats systems, company careers pages, public employment agencies, and direct submissions.
METHOD
PATH
DESCRIPTION
/v1/jobs
Search live listings
/v1/jobs/{id}
Get one listing with its description
/v1/jobs/closed
List roles that left their source
/v1/changes
Read the delta feed
/v1/companies
List employers
/v1/export
Stream the corpus as NDJSON
/v1/meta/facets
Get filter values with live counts
/v1/jobs
Search live listings
/v1/jobs/{id}
Get one listing with its description
/v1/jobs/closed
List roles that left their source
/v1/changes
Read the delta feed
/v1/companies
List employers
/v1/export
Stream the corpus as NDJSON
/v1/meta/facets
Get filter values with live counts
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Job Opportunities API by hand means sending its bearer token, learning dozens of query filters and their absence tokens, and paging with a keyset cursor because offsets are rejected. Through Jentic you install once, import the Job Opportunities API from the API Directory, store the token once, and your agent calls it.
Permission scoping
The listing id and employer slug sit in the URL path (/v1/jobs/{id}, /v1/companies/{slug}), so a rule can bound your agent to specific reads, while search filters travel as query parameters. You choose the operations it may call, so bulk export and export-pack operations that consume plan allowance are not included unless you add them.
Credential isolation
Your Job Opportunities API secret is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find remote jobs' or 'list closed roles', and Jentic returns the matching Job Opportunities operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Job Opportunities API through Jentic.
What authentication does the Job Opportunities API use?
The Job Opportunities API authenticates with a bearer token sent as Authorization: Bearer followed by your API secret, per its OpenAPI spec. The public endpoints under /public, such as site stats and market signal history, are open and need no token. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time.
Is there a Job Opportunities API MCP server?
You don't need an MCP server to give your agent the Job Opportunities API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent searches listings, closed roles, and employers as it needs them. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.
Can I limit what my agent is allowed to do with the Job Opportunities API?
Yes. For example, write a rule that allows only the listing search and single-listing read operations, so a candidate-facing agent can find and read jobs but cannot run bulk exports or queue export packs that draw on your plan's allowance. Because the employer slug is in the path at /v1/companies/{slug}, a rule can also hold an agent to one company's profile, and every call is logged.
How do I find only jobs that are confirmed remote with the Job Opportunities API?
Add remote_confirmed=true to the listing search. Each job's field_sources names every field as published, inferred, or absent, and this filter returns only listings whose remote status the source itself stated rather than one derived by the API.
What are the rate limits for the Job Opportunities API?
The Job Opportunities OpenAPI spec defines a rate-limited response that reports the limit hit in records per month, requests per day, or requests per minute, but it does not publish the numbers. Call GET /v1/me to read your key's plan and quota, and check https://jobopportunitiesapi.org for plan details.
How do I search job listings with the Job Opportunities API through Jentic?
Search Jentic for an intent like 'find remote jobs in a country', import the Job Opportunities API from the API Directory, and store your bearer token once. Your agent then calls GET /v1/jobs with filters such as country and title, passing next_cursor back as cursor to page. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Search employer-direct job listings with filters for country, remote status, salary, seniority, and contract fields, and see which fields the source stated versus inferred. Also reads closed roles, a change feed, employer profiles, and bulk exports.
Use for: Find all remote software engineering jobs in Germany posted this week, I need to see only listings where the employer stated the job is remote, List all roles at a company that closed in the last month, Get the changes to job listings since yesterday
Not supported: Does not handle posting jobs, applicant tracking, or submitting applications. Use for searching and monitoring employer-direct job listings only.
The Job Opportunities API returns employer-direct job listings drawn from employer ATS systems, company careers pages, public employment agencies, and direct submissions. Every job carries field_sources, which marks each field as published by the source, inferred, or absent, and last_verified_at, which records when the vacancy was last confirmed at its source. Alongside live listings it keeps closed roles with their closure reason and date, a delta feed of created, updated, withdrawn, and delisted rows, employer profiles, and bulk NDJSON export for whole-corpus pulls.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>