About jobfeed
jobfeed is a local bridge to Fairquery's jobs MCP service, for reading public job boards and current openings. It supports searches for individual companies and multi-company monitoring, while storing no job data and handling no applications or candidate data.
Key features
- 01Read current jobs on a board
- 02Resolve companies to their boards
- 03Check whether a job remains open
- 04Fetch job details and starter boards
- 05Search jobs by place or company
Use cases
- 01View public openings at a company
- 02Verify whether a specific job is still published
- 03Find boards by location and role
- 04Monitor new, closed, and reposted jobs across companies
MCP support
It serves the upstream job tools locally and forwards MCP calls to the Fairquery Jobs remote service. Upstream results are returned unchanged.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
7Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| ats | enum | Yes | Required. The applicant-tracking system hosting the board: "greenhouse" | "lever" | "ashby" | "personio" | "pinpoint" | "gem". Personio, Pinpoint and Gem are the account, subdomain or vanity you name, not a discovered board. Example: "ashby"greenhouse | lever | ashby | personio | pinpoint | gem |
| slug | string | Yes | Required. Board slug as it appears in the public board URL (case-insensitive): boards.greenhouse.io/{slug}, jobs.lever.co/{slug}, jobs.ashbyhq.com/{slug}, the Personio account in {account}.jobs.personio.de, the Pinpoint subdomain in {subdomain}.pinpointhq.com, or the Gem vanity in jobs.gem.com/{vanity}. Named feeds reject a dot. 1-100 chars. Example: "ramp" or "acme" |
| limit | integer | No | Optional page size, integer 1-500, default 50 |
| offset | integer | No | Optional items to skip, integer >= 0, default 0; pass nextOffset from the previous response |
| remote | enum | No | Optional, "any" | "only" | "exclude", default "any"any | only | exclude |
| countries | array | No | Optional ISO-3166 alpha-2 codes, any-of, case-insensitive. Example: ["US","DE"] |
| locations | array | No | Optional, 0-50 strings, any-of. Substring match on location text. US state names and codes match both ways (FL and Florida); NYC, SF, LA, DC, Tampa Bay and other US metro aliases match. "remote" also matches ATS remote flags. Example: ["new york","berlin"] |
| longOpenDays | integer | No | Optional integer, default 60: rows older than this get long_open = true (a heuristic, not proof of a ghost job) |
| titleExcludes | array | No | Optional, 0-50 strings, any-of. Drop titles containing any of these. Example: ["intern","manager"] |
| titleIncludes | array | No | Optional, 0-50 strings, any-of. Keep titles containing any of these whole words/phrases, case-insensitive. Example: ["engineer","data scientist"] |
| postedWithinDays | integer | No | Optional integer 1-3650: keep jobs whose ATS publish date is at most this many days old. Example: 14 |
| includeDescription | boolean | No | Optional boolean, default false. true adds description_text (plain text, <= 20,000 chars, e-mails/phones removed) |
Details
From the project READMEjobfeed
jobfeed is a small local bridge to the hosted Fairquery jobs MCP server, which reads live job boards from their official public sources. Ask for one company's board, resolve a company to the board it uses, re-check whether a single job is still open, fetch one job in full, list the verified starter boards, or search that starter list by place and role — and, through the paid company search, monitor openings across many companies with history.
The bridge keeps no job data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The captured surface is read-only public job-board data: there is no applying, messaging, or candidate data in it.
Tools
jobs_get_board— every job currently published on one board. Required:atsandslug. Optional filters include title includes/excludes, locations, countries, remote, posted-within days, description inclusion, and paging.jobs_find_board— resolve a company name, domain, or careers/board URL to its public board. Required:company.jobs_check_open— re-check whether one job is still published. Takes ajobKey, orats+slug+jobId, with optionalincludeDescription.jobs_get_job— one published job's full detail, from ajobKeyorats+slug+jobId.jobs_list_seed_boards— the bundled starter list of verified boards, optionally narrowed byats, with paging.jobs_search_by_location— search the starter list by place and role, with no company name. Requires a place signal: locations, countries, or remote"only".jobs_search_companies— the paid multi-company search and monitoring tool, with history, new/closed and repost signals across many companies or boards.
Boards cover Greenhouse, Lever, and Ashby, plus named Personio, Pinpoint, and Gem feeds.
Configuration
FAIRQUERY_JOBS_MCP_URL(optional) — override the upstream endpoint. Defaults tohttps://mcp.getfairquery.com/jobs/mcp. (The override hook is this rebuild's own labelled reconstruction.)FAIRQUERY_JOBS_API_KEY(optional) — when set, every upstream request carries anAuthorization: Bearer <key>header. When it is not set, no key header is sent. The upstream record pins no auth header, so this forwarding is also a labelled reconstruction; the original surface was captured keyless.
Forwarding mechanics
On the first tool call the client opens a streamable
HTTP session with the upstream: a JSON-RPC initialize
request (protocolVersion 2025-03-26, clientInfo name
jobfeed), then a notifications/initialized
notification, then the tools/call request carrying
the caller's arguments unchanged. When the upstream
answers initialize with an Mcp-Session-Id header,
that value rides on every later request of the session,
which is reused for the life of the process. Replies
may arrive as plain JSON or as server-sent events;
both are read.
Successful upstream results pass through verbatim,
including any isError flag the upstream sets.
Failures — a JSON-RPC error, a non-2xx status, an
unreadable response, or a request that cannot be
completed — come back as an isError result whose
text starts with jobfeed error: (this rendering
is this rebuild's own labelled reconstruction).
CLI
Each tool is also a subcommand taking one JSON argument string:
npx @reneturcios/jobfeed jobs_get_board '{"ats":"ashby","slug":"ramp"}'
npx @reneturcios/jobfeed jobs_find_board '{"company":"ramp.com"}'
npx @reneturcios/jobfeed jobs_search_by_location '{"locations":["Costa Mesa"],"descriptionIncludes":["avionics"]}'
npx @reneturcios/jobfeed --version
Exit codes: 0 on success, 1 on an isError
result, 2 on a usage error.
MCP server
npx -y @reneturcios/jobfeed mcp
MCP client config:
{
"mcpServers": {
"jobfeed": {
"command": "npx",
"args": ["-y", "@reneturcios/jobfeed", "mcp"]
}
}
}
Docker
docker run -i ghcr.io/cloudcorprecords/jobfeed
docker run --rm ghcr.io/cloudcorprecords/jobfeed --version
The container's default command is mcp, so the first
form is a stdio MCP server; any other arguments reach
the CLI normally.
Development
npm install
npm run build
npm test
npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.