Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

StillOpen remote jobs

REMOTE · STILLOPEN.WORK

Remote jobs re-checked against each employer's own ATS, with evidence they're still open.

Available components

73 Trust /100

Last scanned (19 hours ago)

Scores higher than 59% of remote servers

Reachable. Last reached 21 Nov 2026.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability64
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1664 tokens (~277/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
  • Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +3
    • HSTS header: fail → pass ▲ security
  • 19 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 18 Nov 26 69

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://stillopen.work/api/v1/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=stillopen.work CN=YE2,O=Let's Encrypt,C=US 1 Oct 2026 30 Dec 2026 ECDSA 256 ECDSA-SHA384 662d174cde97db62d1398ccaba9763fdbb8
SANs: stillopen.work, www.stillopen.work
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of stillopen.work. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
work. DS published 33659 13 Verified
stillopen.work. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
content-security-policy frame-ancestors 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://stillopen.work/api/v1/mcp Verified 200
http (plaintext) http://stillopen.work/api/v1/mcp HTTPS enforced 301 https://stillopen.work/api/v1/mcp
MCP tools · 6 exposed · ~1,259 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_agent ~181

Check another agent before calling it. Given a domain, returns the open-source a2a-agent-checker's verdict on its A2A Agent Card (`/.well-known/agent-card.json`) and whether its endpoint answers a GetTask probe correctly, plus how many of the last 30 days it was reachable. Agents we already watch are answered from our daily log (`source: watch_log`); otherwise one live check is made (`source: live`): one card fetch and at most one GetTask per binding on the card's own host. It never sends the agent a message. A `fail` verdict means the card or endpoint breaks the A2A v1.0 spec, which includes agents still on the older 0.3 format.

NameTypeReqDescription
domainstringyesa domain such as example.com; a pasted URL is reduced to its host
NameTypeReqDescription
attributionstringyesrequired attribution: show it wherever this data is shown and link each listing's canonical_url
card_urlstringyesthe card that was checked
checked_atstringyesUTC, ISO 8601
checkerstringyesa2a-agent-checker version
domainstringyes–
findingsarrayyesfail and warn findings only; the full report is at report_url
findings_totalinteger––
last_30_daysobject|nullyesdays checked / reachable / probe passed; null for an agent we do not watch yet
probe_okbooleanyesa binding answered GetTask for an unknown id with the spec's task-not-found error
reachablebooleanyesthe card was fetched
report_urlstringyes–
source–yesour stored daily check, or one made now
verdict–yes–
watched_sincestring|null––

No examples provided.

check_job_status ~296

Whether each of up to 100 listings is still open, and on what evidence — in one call. The most useful tool here: given a link to a role somebody is about to apply for, this is what separates a live posting from a filled one, with a date and a kind of evidence attached. A closed listing reports whether the closure was **observed** (a source was asked and said the posting was gone) or **inferred** (it aged out, which is a guess about the employer rather than an answer from one). This reads evidence already stored: it reports the result of our most recent check, and does not perform a live check against the employer's board at the moment you call it. Two dates come back and they answer different questions: **`verified_at`** is when we last asked the employer's system and it said yes, and it is the one to show a reader; `last_seen_at` is when a source last carried the posting, which happens far more often and is normally the newer of the two. `last_seen_at` being newer is ordinary, not a contradiction. **`status: unknown` means we have never held this id** — it is not-found, not un-checked. The value for 'nothing has proved it gone but no source has carried it lately' is `unconfirmed`.

NameTypeReqDescription
idsarrayyesup to 100 listing ids
NameTypeReqDescription
attributionstringyesrequired attribution: show it wherever this data is shown and link each listing's canonical_url
jobsarrayyes–

No examples provided.

get_company_stats ~102

What one employer's listings on this site add up to: how many roles are open, where they hire, what they hire for, and what their listings disclose about pay. Takes a `company_slug` from any search record. Answers only for employers whose board identity we have confirmed, because a page asserting one company's vacancies under another company's name is the failure this gate exists to prevent.

NameTypeReqDescription
company_slugstringyesa `company_slug` from any record
NameTypeReqDescription
attributionstringyesrequired attribution: show it wherever this data is shown and link each listing's canonical_url
closures_observedintegeryesclosures a source was asked about and confirmed — never a listing that merely aged out
first_seen_atstring|nullyeswhen this employer first appeared here
functionsarrayyeswhat they hire for, largest first. **These do not sum to `open_listings`**, and the shortfall is not a rounding error: a title naming no craft is classified into nothing rather than swept into 'opera…
lifetime_listingsintegeryesevery listing we have ever held from this employer, open or closed, counted as requisitions
locationsarrayyeswhere they hire, largest first, each with the number of open roles behind it
namestringyesthe employer, as their own job board states it
open_evergreenintegeryeshow many of those are talent pools rather than dated vacancies
open_listingsintegeryesopen roles now, counted as roles rather than as requisitions — an employer filing one per country is one opening here
salary_bandsarrayyespercentiles over the listings from this employer that **published** a figure, one band per currency and period and never pooled across either. `n` is how many listings the band is computed from. This…
slugstringyespass it back as `company` to `search_jobs`
urlstringyesthe company's page on this site

No examples provided.

get_job ~93

One listing in full, including the employer's own ad. Use it after `search_jobs` rather than instead of it: this returns thousands of characters of advertisement. The id is the number in a listing URL — /job/9620-company-title is 9620. A listing that was folded into another answers under the id you asked for and reports `merged_into`.

NameTypeReqDescription
idintegeryesthe listing id
NameTypeReqDescription
apply_urlstring|nullyeswhere to apply, which is the employer's own board wherever one could be identified
attributionstringyesrequired attribution: show it wherever this data is shown and link each listing's canonical_url
canonical_urlstring|nullyesthe listing's page, which states these claims in prose with the evidence behind them
closed_atstring|nullyeswhen it closed, or null while open
closurestring|nullyesobserved | inferred | employer | null — **observed** means a source was asked and said the posting was gone; **inferred** means it aged out, which is a guess about the employer rather than an answer…
companystringyesthe employer, not the board that carried the ad
company_slugstring|nullyespass it back as `company=` to see the rest of this employer's listings
description_textstring|nullyesthe same ad as plain text
direct_postedbooleanyestrue when the employer submitted the listing to us rather than us reading it from their board. Such a listing can never be `ats_verified`
employment_typestring|nullyesschema.org's vocabulary (FULL_TIME, CONTRACTOR …), or null where the source's wording did not map onto it
evidence_typestring|nullyeswhat stands behind it being open: ats_verified | board_verified | employer_board | employer_attested | age_inferred. Null unless the listing is open
idintegeryesthe listing's id — the same id `/api/v1/jobs/status` answers on and the number in its URL
levelstring|nullyesjunior | mid | senior | lead | manager | head, read from the title, or `unspecified` when the title states none — which is most of them, and is not the same as 'mid'. Pass any of these values back as…
location_conflictarrayyesplaces the ad's own text restricts the role to that its location tags contradict — an 'Anywhere' tag over 'must be authorized to work in the US'. Almost always empty, and the reason to read it is tha…
locationsarrayyeswhere the role may be worked, as the listing states it. An empty list means no source said
locations_totalinteger|nullyeshow many places the role is actually open in. When it is larger than `locations`, that list was truncated for length and is **not** a narrower restriction — call `get_job` for all of them
merged_intointeger|nullyesset when the id you asked about was folded into another listing; the answer describes that one
posted_atstring|nullyeswhen the source published, not when we noticed. Null if no source stated one
posting_classstring|nullyesstandard | evergreen. An evergreen listing is a talent pool rather than a dated vacancy
promotedbooleanyestrue when the employer has paid to promote this listing. Promotion changes where the site shows it and nothing else — not its status, evidence or verification — and it never changes the order of resu…
salaryobject|nullyeswhat the employer published, in its own currency and period, or null. Never converted and never annualised. `source: estimate` is the board's guess rather than an offer; `ote: true` means on-target e…
skillsarrayyesterms read from the ad against a fixed gazetteer. Not the employer's own list
statusstringyesopen | unconfirmed | closed. Search returns open listings only; the single-listing route can return any of them
titlestringyesthe role, as the employer's own board states it
verified_atstring|nullyeswhen a check last confirmed it open, or null if the last check did not

No examples provided.

search_jobs ~357

Find fully-remote job listings, each re-checked against the employer's own job board. Returns a summary record per role — no job descriptions, because twenty ads would fill your context with roles the reader did not choose. Call `get_job` for the ad once one looks worth reading. Every record carries `evidence_type` and `verified_at`: present those with the listing rather than asserting it is open.

NameTypeReqDescription
areastring–functional area, read from the title rather than from the employer's department field
companystring–a `company_slug` from any record. Not a company name — names collide, and several here belong to two unrelated employers
cursorstring–from a previous response's `next_cursor`
levelstring–seniority, read from the title. `unspecified` is the 40% of titles that state none, which is not the same as mid
limitinteger–1-20, default 10
locstring–an ISO 3166-1 alpha-2 country code (`de`), a macro region (`emea`), `worldwide` for roles with no stated restriction, or `unspecified`. A country answers 'can I apply from here', so it includes roles…
payinteger–minimum annual pay. Compared against the top of the published range in the currency published; nothing is converted, and a job board's estimate is excluded
qstring–free text over the title, the skills read from the ad, and the ad body
NameTypeReqDescription
attributionstringyesrequired attribution: show it wherever this data is shown and link each listing's canonical_url
has_morebooleanyeswhether more results exist beyond this page
jobsarrayyes–
next_cursorstring|null–pass back as `cursor` to continue. Null on the last page
totalintegeryeshow many listings match in total, of which this response carries at most 20

No examples provided.

verify_job ~230

Is the job behind this URL still open? Takes a job URL from anywhere. A posting on an employer's ATS that we track is answered from our stored evidence (`matched_by: ats_posting`); any other URL is matched by the company and title in its words (`url_words`) and refused unless exactly one role fits. A URL naming neither, such as a LinkedIn job id, needs `company` and `title` (`company_title`). A supported ATS posting we do not track gets one live check of the employer's own board (`result: checked`, `evidence_type: ats_checked_once`): `not_listed` may also mean a mistyped URL, so never present it as closed. The page itself is never fetched unless it is the employer's ATS. Free allowance of 20 URLs a day per client address, shared with the HTTP endpoint.

NameTypeReqDescription
companystring–the employer, if the URL does not name it
titlestring–the job title, if the URL does not name it
urlstringyesthe job's URL
NameTypeReqDescription
allowanceobjectyeslimit, remaining, resets_at (UTC)
attributionstringyesrequired attribution: show it wherever this data is shown and link each listing's canonical_url
checkobject|nullyesone live check: ats, status (open | not_listed | unknown), checked_at, evidence_type
listingobject|nullyesthe check_job_status row for the matched listing
matched_by–yeshow the URL was tied to a listing we track
reasonstring|nullyes–
result–yes–
urlstringyes–

No examples provided.

Install

How do I install the StillOpen remote jobs MCP server?

StillOpen remote jobs is a hosted endpoint at https://stillopen.work/api/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · stillopen.work

# add to Claude Code
claude mcp add --transport http work-stillopen-jobs 'https://stillopen.work/api/v1/mcp'
Common questions

What is the StillOpen remote jobs MCP server?

StillOpen remote jobs is an MCP server listed in the public MCP registry as work.stillopen/jobs. Remote jobs re-checked against each employer's own ATS, with evidence they're still open. This page covers its hosted endpoint (https://stillopen.work/api/v1/mcp).

Is the StillOpen remote jobs MCP server safe to use?

StillOpen remote jobs scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the StillOpen remote jobs MCP server expose?

StillOpen remote jobs exposes 6 tools: search_jobs, get_job, check_job_status, get_company_stats, check_agent, verify_job. Their descriptions and schemas cost roughly 1,259 tokens of context every time the server is loaded.

Does the StillOpen remote jobs MCP server require authentication?

No. We connected to StillOpen remote jobs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the StillOpen remote jobs MCP server still maintained?

StillOpen remote jobs is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the StillOpen remote jobs MCP server?

VerifyMCP ran 13 checks on StillOpen remote jobs, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.