💼 Remote Jobs MCP Server

This MCP server lets Claude, ChatGPT, Cursor, VS Code or any MCP client search remote job openings from several public job boards in one format. It exposes 8 read-only tools: a job search, a single-job lookup, a status check for saved jobs, advertised salary ranges, a hiring snapshot and the filter lists, plus the search and fetch pair that ChatGPT uses for citations.

Ask Claude "which senior Python jobs open to candidates in Europe were posted this week, and what do they pay?" and it calls jobs_search, then jobs_salary_insights. You get the matching jobs with company, advertised salary and a link to each listing, then the median and quartiles of the salaries those listings show. No job board tabs to juggle.

Quick start

1. Copy your Apify API token from Apify Console > Settings > API & Integrations.
2. Point your MCP client at https://mrbridge--remote-jobs-mcp.apify.actor/mcp with that token, as a Bearer header or as ?token= in claude.ai and ChatGPT (Connect has every recipe).
3. Ask in plain language.

What this server exposes

This server reads remote job listings from three job boards: the public Jobicy Remote Jobs API, which covers jobs published on Jobicy in the last 7 days, the Arbeitnow Job Board API, whose newest remote jobs are added with Arbeitnow's permission, and the public Remotive Remote Jobs API, whose active jobs appear 24 hours after their publication on Remotive. It has 6 read-only tools: a job search by keyword, candidate location, category, employment type, seniority, company, minimum yearly salary, recency and job board, a lookup of one job with its current status, a status check for up to 100 saved jobs, advertised salary ranges, a hiring overview (top companies and the mix of categories, types, levels and locations), and the list of location and category values, plus the search and fetch pair for ChatGPT. Every job comes in one normalised schema with its source and its link on that job board, and full descriptions stay there. It needs no API key and no account.

Tools

Tool	What it answers	Billed event
jobs_search	Search remote jobs	tool-read
jobs_get_job	Get one remote job	tool-read
jobs_check_status	Check whether jobs are still open	tool-read
jobs_salary_insights	Remote job salary ranges	tool-action
jobs_market_snapshot	Remote hiring snapshot	tool-action
jobs_list_filters	List location and category filters	tool-read
search	Search	tool-read
fetch	Fetch	tool-read

jobs_search: Search remote jobs

Use this when the user wants remote job openings: by keyword (skill, role, technology), by where candidates may live, by category, employment type, seniority, company, minimum yearly salary or recency. Covers jobs published on Jobicy in the last 7 days, the newest remote jobs of Arbeitnow and the active jobs of Remotive (shown 24 hours after publication), merged newest first. Do not use for salary statistics (jobs_salary_insights), hiring counts and top companies (jobs_market_snapshot), the open or closed status of saved jobs (jobs_check_status), or the filter values (jobs_list_filters). Parameters: keyword (string, e.g. "python"), location (slug or name, e.g. "europe"), category (slug or name, e.g. "engineering"), job_type (e.g. "full-time"), level (e.g. "senior"), company (e.g. "Acme"), min_salary (yearly, e.g. 100000) with salary_currency (default "USD"), posted_within_days (1 to 7), source ("all", "jobicy", "arbeitnow" or "remotive"), limit (1 to 50, default 10), offset, response_format ("detailed" adds a short excerpt and the logo, at most 25 jobs). Each job has an id, title, company, location, types, level, categories, salary as advertised, publication time, its source and its link on that job board. Descriptions are not returned: follow the link. sources says which job boards answered. next_call reads the first job with jobs_get_job.

Parameter	Type	Required	Example
keyword	string	no	"python"
location	string	no	"europe"
category	string	no	"engineering"
job_type	"full-time" or "part-time" or "contract" or "freelance" or "internship" or "temporary"	no	"full-time"
level	"junior" or "mid" or "senior" or "lead" or "manager"	no	"senior"
company	string	no	"Acme"
min_salary	number	no	100000
salary_currency	string	no	"USD"
posted_within_days	integer	no	3
source	"all" or "jobicy" or "arbeitnow" or "remotive"	no	"all"
limit	integer	no	10
offset	integer	no	0
response_format	"concise" or "detailed"	no	"concise"

Returns { jobs[], pagination, filters, coverage, notices[], next_call, sources[], attribution, attributions[] }. Upstream: Jobicy, Arbeitnow, Remotive. Cache: hourly (1 hour). Read-only.

jobs_get_job: Get one remote job

Use this when the user wants one job found by jobs_search: its fields, a short excerpt, its link on the job board and whether it is still open. Do not use for searching (jobs_search) or for checking many saved jobs at once (jobs_check_status). Parameters: job_id (required, an id from jobs_search such as "jobicy:4401008", "arbeitnow:

Parameter	Type	Required	Example
job_id	string	yes	"jobicy:4401008"
keyword	string	no	"python"
location	string	no	"europe"
category	string	no	"engineering"
response_format	"concise" or "detailed"	no	"concise"

Returns { job, status, notices[], attribution }. Upstream: Jobicy, Arbeitnow, Remotive. Cache: hourly (1 hour). Read-only.

jobs_check_status: Check whether jobs are still open

Use this when the user wants to know whether saved or earlier found jobs are still open, up to 100 at once, Jobicy jobs older than the 7-day feed included. Do not use for finding jobs (jobs_search) or reading one job's fields (jobs_get_job). Parameter: job_ids (array of 1 to 100 ids from jobs_search such as "jobicy:4401008", "arbeitnow:

Parameter	Type	Required	Example
job_ids	array of values	yes	["jobicy:4401008","jobicy:4401007"]

Returns { jobs[], summary, checked_at, attribution, attributions[] }. Upstream: Jobicy, Arbeitnow, Remotive. Cache: intraday (5 minutes). Read-only.

jobs_salary_insights: Remote job salary ranges

Use this when the user asks what remote jobs pay: salary ranges, median and quartiles for a skill, role, category, location, employment type or seniority, from the salaries advertised in Jobicy listings of the last 7 days and in active Remotive listings. Do not use for a list of openings (jobs_search) or hiring counts (jobs_market_snapshot), and do not read it as a market survey: it covers advertised ranges of recent remote listings only. Parameters: keyword (e.g. "data scientist"), location (e.g. "usa"), category (e.g. "data-science"), job_type (e.g. "full-time"), level (e.g. "senior"), salary_currency (optional, keeps one currency, e.g. "EUR"), response_format ("detailed" adds the median per level and five top-paying jobs instead of three). Statistics are computed per currency and pay period on the midpoint of each advertised range, never converted. The answer says how many matching jobs list a salary and how much of the 7-day window was read. Remotive salary texts count only when their amounts, currency and period are clear. Arbeitnow listings carry no salary, so they are not used here.

Parameter	Type	Required	Example
keyword	string	no	"python"
location	string	no	"europe"
category	string	no	"engineering"
job_type	"full-time" or "part-time" or "contract" or "freelance" or "internship" or "temporary"	no	"full-time"
level	"junior" or "mid" or "senior" or "lead" or "manager"	no	"senior"
salary_currency	string	no	"USD"
response_format	"concise" or "detailed"	no	"concise"

Returns { filters, jobs_matched, jobs_with_salary, salary_disclosure_rate, groups[], highest_paying[], coverage, notices[], sources[], attribution, attributions[] }. Upstream: Jobicy, Remotive. Cache: hourly (1 hour). Read-only.

jobs_market_snapshot: Remote hiring snapshot

Use this when the user wants an overview of recent remote hiring for a keyword, location or category: how many jobs, which companies post the most, the split by category, employment type, seniority and location, and how many listings show a salary. Do not use for the openings themselves (jobs_search) or for salary figures (jobs_salary_insights). Parameters: keyword (e.g. "rust"), location (e.g. "europe"), category (e.g. "marketing"), source ("all", "jobicy", "arbeitnow" or "remotive"), top (entries per breakdown, 1 to 20, default 8), response_format ("detailed" adds jobs per publication day). Counts cover Jobicy listings of the last 7 days (at most the 1,000 newest per call), the newest remote Arbeitnow listings and the active Remotive listings, a job on several boards counted once. Arbeitnow tags and Remotive categories count as categories. The coverage block says whether the Jobicy window was read in full, sources which job boards answered. Shares are fractions of the jobs counted.

Parameter	Type	Required	Example
keyword	string	no	"python"
location	string	no	"europe"
category	string	no	"engineering"
source	"all" or "jobicy" or "arbeitnow" or "remotive"	no	"all"
top	integer	no	8
response_format	"concise" or "detailed"	no	"concise"

Returns { filters, jobs, top_companies[], by_category[], by_job_type[], by_level[], by_location[], salary_disclosed, per_day[], coverage, notices[], sources[], attribution, attributions[] }. Upstream: Jobicy, Arbeitnow, Remotive. Cache: hourly (1 hour). Read-only.

jobs_list_filters: List location and category filters

Use this when the user wants the locations (where candidates may live) or job categories the remote job search accepts, or when a location or category was refused as unknown. Do not use for finding jobs (jobs_search). The search tools already accept display names such as "United States" or "Software Engineering", so this call is only needed to browse or to settle an unknown value. Parameters: kind ("locations", "categories" or "both", default "both"), query (optional part of a name, slug or common alias, e.g. "united"), response_format ("detailed" adds cache information). Each value has a slug, the form the search tools send to Jobicy, and a display name.

Parameter	Type	Required	Example
kind	"locations" or "categories" or "both"	no	"locations"
query	string	no	"united"
response_format	"concise" or "detailed"	no	"concise"

Returns { locations, categories, notice, attribution }. Upstream: Jobicy. Cache: daily (1 day). Read-only.

search: Search

Use this when ChatGPT needs remote job openings for a free-text query such as "senior rust jobs in europe": the useful words become a keyword, a location named in the query becomes a filter, and the 10 newest matching jobs of Jobicy (last 7 days), Arbeitnow (newest remote jobs) and Remotive (active jobs, 24 hours after publication) come back with their job board page as citation. Do not use for details, call fetch with a result id. Parameter query (string), e.g. "python developer europe".

Parameter	Type	Required	Example
query	string	yes	"python developer europe"

Returns { results[], notices[] }. Upstream: Jobicy, Arbeitnow, Remotive. Cache: hourly (1 hour). Read-only.

fetch: Fetch

Use this when ChatGPT needs one job returned by search: title, company, location, type, level, category, advertised salary, publication time, current status, a short excerpt and the job board link. Do not use for free-text queries (call search first). The full description stays on the job board page. Parameter id (an id from search, a Jobicy id, or a Jobicy, Arbeitnow or Remotive job link), e.g. "jobicy:4401008?keyword=python".

Parameter	Type	Required	Example
id	string	yes	"jobicy:4401008?keyword=python"

Returns { id, title, text, url, metadata, notices[] }. Upstream: Jobicy, Arbeitnow, Remotive. Cache: hourly (1 hour). Read-only.

Connect

Endpoint (Streamable HTTP): https://mrbridge--remote-jobs-mcp.apify.actor/mcp

Every client authenticates with your Apify API token, found in Apify Console > Settings > API & Integrations. Clients that support custom headers send it as Authorization: Bearer <token>. The others use the ?token= URL variant, which must be treated as a secret: keep it out of commits, screenshots and shared logs.

Claude Code

$claude mcp add --transport http remote-jobs "https://mrbridge--remote-jobs-mcp.apify.actor/mcp" --header "Authorization: Bearer ${APIFY_TOKEN}"

Cursor, VS Code and other JSON configurations

{
  "mcpServers": {
    "remote-jobs": {
      "type": "http",
      "url": "https://mrbridge--remote-jobs-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer ${APIFY_TOKEN}"
      }
    }
  }
}

claude.ai and Claude Desktop

Add a custom connector with the URL https://mrbridge--remote-jobs-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN and no authentication. Prefilled link (replace the token placeholder before saving): add Remote Jobs MCP Server to Claude.

ChatGPT (developer mode)

Settings > Apps > Create, URL https://mrbridge--remote-jobs-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN, authentication "No authentication". ChatGPT snapshots the tool list: after a server update, an admin has to click Refresh on the app.

OpenAI Responses API

{
  "type": "mcp",
  "server_label": "remote_jobs",
  "server_url": "https://mrbridge--remote-jobs-mcp.apify.actor/mcp",
  "headers": {
    "Authorization": "Bearer YOUR_APIFY_TOKEN"
  },
  "require_approval": "never"
}

Add allowed_tools to restrict the tool list. Tool calls must finish within about 60 seconds on this API, and every tool of this server answers in under 50 seconds.

Anthropic Messages API

{
  "mcp_servers": [
    {
      "type": "url",
      "url": "https://mrbridge--remote-jobs-mcp.apify.actor/mcp",
      "name": "remote-jobs",
      "authorization_token": "YOUR_APIFY_TOKEN"
    }
  ],
  "tools": [
    {
      "type": "mcp_toolset",
      "mcp_server_name": "remote-jobs"
    }
  ]
}

Send the beta header anthropic-beta: mcp-client-2025-11-20.

One-click OAuth alternative

https://mcp.apify.com/?tools=mrbridge/remote-jobs-mcp connects through Apify OAuth without a token. It exposes the Actor as a single tool rather than the granular tools listed above.

Cost control

Each Standby run has a spending limit (maxTotalChargeUsd). When a call uses the last of it, the result is still returned, and later calls in that run answer CHARGE_LIMIT_REACHED until the limit is raised.

Why use this server

• Several job boards, one answer. Listings come back merged, newest first, with the same fields: title, company, location, type, level, category, salary, date, source and link. A job posted on two boards appears once.
• Plain-language filters. Location and category accept names such as "United Kingdom" or "web design", and a typo gets the closest valid values back instead of an empty list.
• Salary figures you can check. Salary ranges, with their median and quartiles, are computed from the salaries employers advertise, per currency and pay period, never converted. Each answer says how many listings showed a salary.
• Still open or not? Send up to 100 saved job ids and see which ones are active, closed or unknown, older Jobicy jobs included.
• Credits handled. Every job keeps its source and its link, and every answer carries the credit each job board asks for.
• No key at the job boards. You connect with your Apify token. You pay per successful call, plus the platform usage of your own server run.

Pricing (Pay-per-Event)

Event	Charged when	Price
apify-actor-start	run start (platform default)	see the Store page
tool-read (primary event)	each successful read tool call	see the Store page
tool-action	each successful call of a detailed or computed tool	see the Store page

Never charged: initialize, tools/list, pings, readiness probes, and any call that ends in an error (invalid input, not found, upstream failure, timeout, spending limit).

Platform usage comes on top of these events. This server runs in Apify Standby mode, and you also pay the platform usage of your own Standby run, billed to your Apify account like any other run: the memory set for the Standby run, for as long as the server is up, idle time included, until the run stops at its idle timeout. The Apify pay-per-event documentation says so: "For runs in Standby mode, users always pay the platform usage costs in addition to the event charges."

Limits, caveats and attribution

• Three sources. Listings come from Jobicy, Arbeitnow and Remotive. Each job carries its source ("Jobicy", "Arbeitnow" or "Remotive") and an id of the form jobicy:<id>, arbeitnow:<slug> or remotive:<id>. Answers merge the boards newest first and say in sources which boards answered. A job posted on several boards (same company and title) shows once: from Jobicy if it is there, else from Remotive. When a board fails, the answer holds the jobs of the others with a notice. source limits a search or a snapshot to one board.
• 7-day window, 3-hour delay. The Jobicy feed holds jobs published in the last 7 days, shown 3 hours after publication. A job that leaves the feed can still be open: jobs_check_status reads the current status of any Jobicy id, older ones included. unknown there is not a confirmed closure.
• Arbeitnow's newest remote jobs. Only remote jobs are kept from Arbeitnow, read from one page of its feed at most once an hour. That page holds the newest listings of every kind, so it usually gives about a dozen remote jobs, and the sources block says how many. Arbeitnow publishes no job status, so jobs_check_status calls an Arbeitnow job active while it is in that feed and unknown once it is not. Arbeitnow gives the place where the employer is based, not the regions candidates may live in, and lists no Jobicy category, seniority or salary. So its jobs are left out of searches with a location, a category, a level or a minimum salary, and of the salary statistics, and the sources block says so. Its tags appear as categories.
• Remotive's active jobs, a day late. Remotive's public feed lists its active remote jobs 24 hours after they go up on Remotive, and every answer with Remotive jobs says so. This server reads the whole feed once a day and answers every question from that copy, so a new Remotive job can take up to two days to show up here. Remotive lists active jobs only: jobs_check_status calls a Remotive job active while it is in that copy and unknown once it is not. Remotive gives the regions candidates may live in as free text and has its own categories and no seniority. So its jobs are left out of searches with a location, a category or a level, and the sources block says so. Its salaries are free text too, read only when the amounts, one currency and one plausible pay period are clear. Those jobs count in a minimum salary filter and in the salary statistics. At most the 3,000 newest Remotive jobs are kept from one read, and the sources block says when older ones were left out.
• At most 1,000 jobs per call. A search reads up to 5 pages of 200 jobs, newest first. The coverage block says how many jobs were read and whether the whole 7-day window was covered. When it was not, add a keyword, a location or a category. Totals in a search are then lower bounds, and the answer says so. Pages of a search reach its first 1,000 matching jobs, all job boards together.
• Excerpts, not descriptions. Job descriptions belong to the employers. Answers carry a short excerpt (at most 400 characters, in detailed mode) and the listing link on Jobicy, Arbeitnow or Remotive, where the full description and the application are.
• Contact details removed. E-mail addresses, phone numbers and links in titles and excerpts are replaced by markers such as [e-mail removed] before anything is cached or returned.
• Keywords. Jobicy searches keywords of 3 to 50 bytes, and several words must all appear. For Arbeitnow, this server looks for every word in the title, company, tags and excerpt. A keyword of 1 or 2 characters ("AI", "Go") is matched as a whole word in job titles instead, with a notice. Locations and categories accept Jobicy slugs, display names or common names such as "United Kingdom" for Jobicy's "UK" (jobs_list_filters lists them), and an unknown value is refused with the closest names.
• Filters done by this server. Employment type, seniority, company, minimum salary and recency are applied by this server to the pages it reads. Seniority relies on the level Jobicy shows, and jobs without one are left out of a seniority filter. Jobicy has no lead level and lists lead and principal roles as senior or director, so for "lead" the job title decides among those. A minimum salary keeps yearly salaries in the chosen currency only.
• Salaries and counts. Salary statistics and hiring counts are computed by this server from advertised ranges. Salaries are grouped by currency and pay period and never converted, and many listings advertise no salary (salary_disclosure_rate shows how many do).
• Reading a job back. None of the APIs has a single-job endpoint, so jobs_get_job and fetch read a Jobicy job again from the search that found it, an Arbeitnow job from the cached Arbeitnow page and a Remotive job from the cached Remotive feed. Pass the next_call arguments of jobs_search, or the ids search returns, as they are.
• Rate limits and freshness. Jobicy publishes no number, only fair use and hourly synchronisation. This server keeps to 15 requests per minute and 300 per hour per instance, caches feed pages for an hour, filter lists for a day and statuses for 5 minutes. Arbeitnow allows 3 requests per minute: this server keeps to half of that, reads one page an hour for every question, and never retries a failed request. Remotive advises at most 4 reads a day and blocks more than 2 requests a minute: this server reads its feed once a day for each Apify account that runs it, never retries a failed read, and makes at most 1 request a minute and 3 in any 24 hours per instance. A busy period can answer UPSTREAM_RATE_LIMITED: retry a minute later.
• Attribution. Every answer has an attribution block for its main source, and the search, snapshot, salary and status answers an attributions list with one block per source shown, each crediting its job board with its link and terms page. The ChatGPT answers carry the same lines in notices. Keep the credit, the source and the link of each job when you show them.
• Affiliation. This server is not affiliated with or endorsed by Jobicy, Arbeitnow or Remotive.

Data terms

The listings come from the public Jobicy Remote Jobs API, under the fair use terms at https://jobicy.com/jobs-rss-feed. Jobicy lets products, AI assistants included, use the listings without a separate agreement, on conditions that also bind you when you reuse what this server returns:

• Credit Jobicy and keep the link. Keep Jobicy as the original source and keep each job's Jobicy URL when you display it. Do not remove the attribution.
• Do not present the listings as your own. They are job postings published by the employers on Jobicy.
• No spam or misleading job databases. Do not use the listings to build spam networks, misleading job boards or services that harm employers or candidates.
• Ask Jobicy for high volumes. Jobicy asks high-volume commercial partners to contact it: https://jobicy.com/contact.

The Arbeitnow listings come from the public Arbeitnow Job Board API, which this server uses with Arbeitnow's written permission (October 2026) for remote jobs, read at most once an hour, within its rate limit. The conditions travel with the listings:

• Name Arbeitnow and link back. Each Arbeitnow job keeps its source and the link to its page on Arbeitnow (arbeitnow.com or a country site such as arbeitnow.ch). Show both with the job.
• Do not present the listings as your own. They are job postings published by the employers on Arbeitnow.

The Remotive listings come from the public Remotive Remote Jobs API, under the terms of its documentation at https://github.com/remotive-com/remote-jobs-api. Remotive was asked on 2026-10-06 whether a paid service such as this one may show them, and has not answered yet. They are shown in the meantime, and they will be withdrawn if Remotive says no or complains. The conditions of the API travel with the listings:

• Name Remotive and link back. Each Remotive job keeps its source and the link to its page on Remotive. Show both with the job.
• Say that the jobs are delayed. The public feed shows jobs 24 hours after their publication on Remotive.
• Do not repost the listings to other job sites. Remotive asks that its jobs are not submitted to third-party job sites, Jooble, Neuvoo, Google Jobs and LinkedIn Jobs included.
• Do not trade the listings for sign-ups. Remotive treats showing its jobs in exchange for sign-ups or e-mail addresses as a breach of its terms.

The fee for this server pays for the service (hosting, caching, normalisation, filters and the statistics it computes), not for a licence on the listings, which Jobicy, Arbeitnow and Remotive offer for free.

Use cases

• Job hunting with an assistant. A candidate asks Claude for remote data engineering roles posted in the last 3 days, then gets a shortlist with a link to each listing.
• Salary benchmarking. Recruiters and career coaches check what recent remote listings advertise for a role and a seniority level before an offer or a negotiation.
• Application tracking. An agent re-checks a list of saved applications every morning and flags the listings that closed.
• Hiring signals. Analysts see which companies post the most remote roles in a category this week, and how seniority and employment types split.
• Cited answers in ChatGPT. Deep research links each job to its board page through the search and fetch pair.

More work and productivity tools

• AI task management with Todoist: Todoist tasks, projects and labels managed from Claude, with prioritization and a daily digest.

FAQ

Which job boards does it cover?

Three public feeds today: Jobicy (jobs published in the last 7 days, shown 3 hours after publication), Arbeitnow (its newest remote jobs, read once an hour) and Remotive (its active remote jobs, shown 24 hours after publication and read once a day). It does not cover the whole remote job market. The sources block of each answer says which boards answered.

Does it return full job descriptions?

No. Descriptions belong to the employers. Answers carry a short excerpt of up to 400 characters and the link to the listing, where the full text and the application form are.

Why do some searches return Jobicy jobs only?

Arbeitnow and Remotive listings use neither Jobicy's regions nor its categories, and carry no seniority level, so they drop out when you filter on one of those. Arbeitnow shows no salary either, so a minimum salary leaves it out too. A keyword search without those filters shows every board.

What does a call cost?

Each successful tool call is one event, at the price shown on the Pricing tab for your Apify plan: tool-action for jobs_salary_insights and jobs_market_snapshot, tool-read for every other tool. Paid Apify plans get lower prices. On the free plan, a read costs $0.005 and an action $0.01, so 100 reads come to $0.50 in events. On top of that, your Apify account pays the platform usage of your own Standby run while the server is up, idle minutes included. Errors are never charged, and maxTotalChargeUsd caps what one run can spend.

Why is the first call slower?

The first call after a quiet period starts a new Standby run on your Apify account, which takes a few seconds. Then it answers quickly, and it shuts down after about 5 idle minutes.

Is this server affiliated with Jobicy, Arbeitnow or Remotive?

No. It reads their public APIs, Arbeitnow's with its permission, and credits each board in every answer. None of them endorses it.

Your feedback

Found a bug or missing a filter? Open an issue on the Issues tab and we will answer there.

More MCP servers, scrapers and data studies from the same team: mr-bridge.com.

Changelog

• 0.3.3: Output, dataset and key-value store schemas, as Apify asks for publication: the Output tab of a run started from the Console shows the connection details and one row per tool.
• 0.3.2: the Input tab shows the endpoint and how to connect an AI client, and a run started from the Console outputs the connection details and the tool list
• 0.3.1: pricing events tool-read and tool-action
• 0.3.0: Remotive is a third source next to Jobicy and Arbeitnow (its active remote jobs, shown 24 hours after publication and read once a day). Searches, snapshots, salary statistics and the ChatGPT pair include Remotive jobs, source accepts "remotive", and jobs_get_job, jobs_check_status and fetch accept remotive:<id> ids and Remotive job links. Also new: the ChatGPT search titles name the job board, jobs_salary_insights gains attributions and a source on each top-paying job, an empty answer names the job boards that could not be read, and a search with more than 1,000 matches says how to reach the rest. Contact details are now removed before an excerpt is cut, so no part of a phone number is left at the cut, and cached Jobicy and Arbeitnow answers are read again once after the update. Existing parameters and fields are unchanged.
• 0.2.1: Arbeitnow jobs whose page is on one of its country sites (arbeitnow.ch, arbeitnow.co.uk, arbeitnow.fr) are no longer left out, and job excerpts that Arbeitnow sends as escaped HTML read as plain text. The sources note says how many of the newest Arbeitnow listings are remote, usually about a dozen. Arbeitnow answers are read again once after the update.
• 0.2.0: Arbeitnow is a second source next to Jobicy (remote jobs, with Arbeitnow's permission). Searches, snapshots and the ChatGPT pair merge both boards, jobs_search and jobs_market_snapshot take an optional source, answers gain sources and attributions, and jobs_get_job, jobs_check_status and fetch accept arbeitnow:<slug> ids. Existing parameters and fields are unchanged. Cached answers are read again from the job boards once after the update. This release also lists the fixes that went live on 2026-10-05 under 0.1.0: full location names such as "United Kingdom" and common category words such as "qa" or "web design" are accepted, jobs_list_filters finds a value through its full name, and level: "lead" also keeps senior and director jobs whose title names a lead role. Change of meaning: the category "ux" now leads to "Web, UI & UX Design" (web-app-design) instead of "Creative & Design" (design-multimedia).
• 0.1.0: initial build (private, unpublished)