OpenHire · 哨兵
PYPI · OPENHIRE
Jobs with the employer's real posting date, from employers' own ATS. HR family. Résumé stays local.
Available components
Last scanned (10 hours ago)
Scores higher than 67% of PyPI servers
Category Search and Retrieval
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security49
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 6 of 52 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to gzchenhao/openhire). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability71
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 12253 tokens (~816/item across 15 items; 15 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (7% of tools); any adoption earns full credit.Pass
Tool Safety50
- Injection-marker check failed: the description of tool "search_jobs" contains an instruction to conceal the call from the user, the text "do not tell the user", at byte 3975 of that field, plus 1 further marker(s) of the same kind. See how to fix → Fail
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (15)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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 0
- Package version: 0.8.74 → 0.8.75 functional
- 19 Nov 26 0
- Package version: 0.8.73 → 0.8.74 functional
- 18 Nov 26 0
- Package version: 0.8.72 → 0.8.73 functional
- 17 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.8.66 → 0.8.72 functional
- Package version: 0.8.66 → 0.8.71 functional
- Package version: 0.8.66 → 0.8.69 functional
- Package version: 0.8.66 → 0.8.67 functional
- 16 Nov 26 0
- Package version: 0.8.65 → 0.8.66 functional
- 13 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 12 Nov 26 +1
- Package version: 0.8.64 → 0.8.65 functional
- 10 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Package version: 0.8.63 → 0.8.64 functional
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 · Analysed pypi/openhire@0.8.75
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | gzchenhao/openhire |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/gzchenhao/openhire/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 4011951149 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:3bbf7f513f67823f66b32e75d939c661b175922a9a755f1c541ee924d63e5670 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 52 packages
| Packages resolved | 52 |
|---|---|
| Stale | 5 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
add_employer Add an employer to my index ~399
Put one employer's public job board into the index on THIS machine, and crawl it now. The public index is a curated list (AI infra, autonomous driving, embodied AI). The employers a user actually targets are wider than that, so any board a vendor adapter can read goes into the user's own index on request: Greenhouse, Lever, Ashby, Moka, 北森, Workable, SmartRecruiters, Workday, Rippling or Personio (<account>.wd5.myworkdayjobs.com/<site>), any sector. After this call the employer behaves like a seeded one: search_jobs(company=...) with the board's own posting dates, days_open and ghost_score; watch_intent on it; refresh_index re-crawls it; the weekly refresh keeps it. It is flagged user_added, is never part of the public snapshot, and remove_employer takes it out. Use it when the user names an employer this index does not carry and has its careers URL (read_board shows the board first without storing anything; add_employer is the step after, when the user wants it watched). A closed portal (Feishu Hire, SuccessFactors, Taleo, iCIMS, LinkedIn, BOSS直聘) is refused with the reason, as read_board refuses it. Privacy: the vendor sees the same tenant read the weekly crawl makes; nothing about the user is sent anywhere, and which employers a user added stays on this machine. Args: url: the careers or board URL as the user pasted it. name: the employer's display name (defaults to the board's tenant name). Returns: added, company_id, jobs_indexed, count_on_board, and suggest_for_public_index, a prefilled GitHub issue link the user may open to propose the employer for everyone.
| Name | Type | Req | Description |
|---|---|---|---|
| name | – | – | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
authorize_application Authorize application ~297
Record an authorized, employer-direct application. REFUSES résumés. Idempotent: the same fingerprint authorizing the same job again gets the original receipt back (`already_authorized: true`); no second record is written. (Formerly `apply` — renamed to make explicit that this only records the user's authorization to apply as themselves; it never submits anything on their behalf.) This tool never accepts a résumé, file, cover letter, name, email or phone — a résumé never transits the server. It only takes a job_id, an anonymous fingerprint, and an explicit per-job authorization. On success it returns the apply_channel (the employer's own application URL) for the user to submit as themselves, plus resume_transmitted=false. Do NOT paste résumé content into any argument. REFUSES means refuses: any argument this tool does not declare (a `resume` key, a `cv`, a `file`, anything) is answered with ERR_PII_NOT_ACCEPTED and nothing is recorded. It is not silently dropped, so a client that sends one finds out. Args: job_id: the job to apply to (from search_jobs / check_watches). fingerprint: the user's anonymous fingerprint. authorized: must be true — explicit per-job consent.
| Name | Type | Req | Description |
|---|---|---|---|
| authorized | boolean | yes | – |
| fingerprint | string | yes | – |
| job_id | string | yes | – |
No output schema declared.
No examples provided.
check_applications Check applications ~364
An answer to "I applied and heard nothing: are they even still hiring?". Follows the postings this fingerprint applied to and reports, from the employer's own system, whether each is still live, has been taken down since (`closed`: stop waiting on it), or has not been returned by the employer's system for 30 days (`not_verified_recently`). Postings recorded with authorize_application are included automatically. When the user says they applied to postings found in this index (on the employer's site or anywhere else), pass those job_ids as `add_job_ids` to follow them; `remove_job_ids` stops following ones they added. Only job_ids are stored, keyed by the anonymous fingerprint: never a name, résumé or where they applied from. Start your answer with the `summary` sentence, then list `closed` first, then `not_verified_recently`, then `open`, quoting each row's `status_in_words`. Do not say an employer ignored the user or that a closed posting was filled: we see the posting, never the employer's inbox. Call it again at the start of a later session to see what changed. Args: fingerprint: the user's anonymous fingerprint (the same one their watches use). add_job_ids: job_ids (from search_jobs) the user says they applied to. remove_job_ids: job_ids to stop following. On the hosted endpoint (results carry `hosted_reset_note`) these records are deleted at every redeploy of the host; relay that note once, and keep the user's conditions so they can redo it.
| Name | Type | Req | Description |
|---|---|---|---|
| add_job_ids | – | – | – |
| fingerprint | string | yes | – |
| remove_job_ids | – | – | – |
No output schema declared.
No examples provided.
check_employer Check an employer ~1,574
Facts about one employer, each with a source and a time. Never a score or a verdict. Use it when the user asks "is this company real / legit / what it says it is?" or is about to apply somewhere they have never heard of. It answers with a checklist, not a judgement: a company can fail an item and be fine (a young domain, an overseas site with no ICP record) or pass every item and still waste the user's time. Relay the items; do not total them, and do not call a company "safe" or "a scam" on this basis. What runs for free, with nothing from the user: * `in_index`: whether the employer's own system is in this index, how many postings are live, the median days open, whether the posting dates are the employer system's own or self-reported (`date_source`), whether the employer claimed its tenant. For an employer we know but do not index (Feishu-hosted, 蔚来, or one that has ceased operations) the item says that instead. * `domain_age` (RDAP registration date; under 180 days is reported, not judged), `site_history` (earliest Wayback Machine capture), `icp_on_homepage` (the ICP 备案号 the employer's own homepage carries, if any). These need the employer's own domain: pass `domain` when the employer's careers page is on a vendor host. * `posting_red_flags`: when the user pastes the posting text, the words recruitment scams rely on (境外高薪, 包机票, 不限经验, 打字员, visa provided ...) are listed if present. Absence proves nothing; presence is worth saying out loud. * `sanctions_screen`: the OFAC SDN and consolidated sanctions lists, downloaded to the user's machine at most once a day and matched against the company's name there (the name is sent nowhere). A match names the entry, list and programme; it is a reason to read the entry, not a verdict, since names collide. A live company registration proves little on its own: Prince Group's Hong Kong companies were on the register the day they were sanctioned. * `org_events`: the organisational and financing events…
| Name | Type | Req | Description |
|---|---|---|---|
| company | – | – | – |
| domain | – | – | – |
| job_id | – | – | – |
| message_text | – | – | – |
| posting_text | – | – | – |
No output schema declared.
No examples provided.
check_watches Check watches ~430
Pull matches that are new since this fingerprint's last check. stdio has no server push, so clients pull: call this at the start of a session. Returns the new matches per watch and advances each watch's last-notified marker. A board watch (registered with board_url) is read live here: its entry carries `new_matches` (appeared on the board since the last pull), `closed_since_last` (gone from the board) and `total_matching`; a board that does not answer comes back as `board_error` and nothing is marked closed on its account. The FIRST pull on a watch returns everything matching it, not an increment: nothing has been reported for that watch before. On that pull the postings are under `baseline_postings` with `baseline_count`, `new_matches` is empty and `is_first_pull` is true; the top-level `new_matches` counts only increments and `baseline_count` the baselines. Never present a baseline to the user as "postings that appeared since last time". Rows are compact (title, company, location, pay, dates_in_words, check_before_apply, apply link and the protocol fields; see `fields`): a full first pull used to run to 68,000 characters and get cut off. search_jobs with the job_id or company gives the full row. Each result also carries `total_matching` and `truncated`: a broad watch can match hundreds of postings and only the 100 best-ranked are returned. Tell the user when `truncated` is true; the rest is not re-reported later. Start your answer with the `summary` sentence (top level and per watch): it already says whether this is the first-pull baseline or an increment, and how many. On the hosted endpoint (results carry `hosted_reset_note`) these records are deleted at every redeploy of the host; relay that note once, and keep the user's conditions so they can redo it.
| Name | Type | Req | Description |
|---|---|---|---|
| fingerprint | string | yes | – |
No output schema declared.
No examples provided.
get_company_info Company trust signals ~682
Aggregate, anonymous trust signals for one employer. Returns ghost_score_avg, active_jobs, and index_built_at (when the index was last built). NEVER returns any individual candidate data: the server holds none. `posting_dates_reported` is false when no live posting of this employer carries the employer's own posting date (first-party mirrors such as Li Auto report none), and `postings_without_reported_date` counts those rows; their days_open, and so this employer's median_days_open and ghost_score_avg, are counted from the day this index first saw each posting, a lower bound on age rather than the employer's timeline. `active_jobs` and every aggregate count only postings the employer's own system returned within the last 30 days of this index; `unverified_over_30d` counts the ones it still holds that went unconfirmed longer (most often a careers board that moved). Those are not shown by search_jobs. Nonzero means a gap in our reading, never a fact about the employer. `claimed` is true only when the employer has claimed this tenant and we verified them by corporate identity, never by payment, and it never affects ranking. It is the only signal here that comes from the employer rather than from their public ATS data, and it is what makes `response_sla_days` non-null on their postings. `hiring_trend` counts what the employer's own system shows: postings published in the 30 days up to the index's newest verification, the 30 days before, and postings taken down in the last 30, with `in_words` (zh, en) to quote. Use it when the user is about to sign or bet months on an internship and asks whether the company is growing or shrinking. Report the counts; never turn them into "they are about to lay off" or "safe to join". Takes an id or any part of the name in either language, like search_jobs' `company`. Known-but-not-indexed employers (Momenta, 小马智行 Pony.ai, 智元 AgiBot, MiniMax, 智谱 Zhipu, 商汤 SenseTime, 逐际动力 LimX, 自变量 X Square, 千寻智能 Spirit AI, 加速进化 Booster, 穹彻智能 Noema…
| Name | Type | Req | Description |
|---|---|---|---|
| company_id | string | yes | – |
No output schema declared.
No examples provided.
get_job Read one posting ~290
One posting by job_id, with the employer's own description as the index holds it. Use it when the user asks what a posting actually involves (is this really product work, does it lead people, what does it require) or before evaluate_fit / tailor_cv. Take job_id from search_jobs, check_watches or check_applications; read_board rows are not in the index (read_board already returns their text). Returns the same fields as a search_jobs row plus `description` (`max_chars` characters from `offset`; follow `description_next_offset` until it is null for a long one), `description_total_chars` and `status`: live, closed (taken down; still shown so the user can read what they applied to, never offer it as an opening) or not_verified_recently (run refresh_index before applying). Quote the text; do not add duties, requirements or visa terms it does not state. Nothing about the user is sent or stored. Args: job_id: e.g. "lixiang:12345", from another tool's result. max_chars: 1 to 20000 characters of description per call (default 8000). offset: where to start in the description (default 0).
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
| max_chars | integer | – | – |
| offset | integer | – | – |
No output schema declared.
No examples provided.
list_portals Careers portals OpenHire cannot read ~291
The blind spots as a link directory: employers in AI infra, autonomous driving and embodied AI whose postings this index cannot read, each with its own careers portal. Most are Chinese employers on Feishu Recruitment (飞书招聘), whose job-list API needs a request signature this index treats as access control; a few publish only on BOSS直聘 or keep a careers page without a readable list. Their postings are public to a person in a browser; OpenHire cannot index, date or watch them. Use it when the user asks about these sectors broadly (具身智能有哪些公司在招, autonomous driving roles in Shanghai), after the search_jobs results: say which employers post elsewhere and give the links, so a blind spot is one click away instead of invisible. If you have a browser tool, offer to open a portal. Never present these links as OpenHire postings and never invent posting dates for them. Args: sector: autonomous_driving, embodied_ai or ai_infra (自动驾驶, 具身, 大模型 work too); leave it out for all three. Returns: PortalDirectory with portals[] (name, careers_url, what a browser shows without logging in, why the employer is not indexed, last_checked) and a note on what OpenHire does not do with them.
| Name | Type | Req | Description |
|---|---|---|---|
| sector | – | – | – |
No output schema declared.
No examples provided.
manage_watch Manage watches ~164
List, change or delete the user's watches (the fingerprint's standing intents). action "list": every active watch with its watch_id and filters. "update": replace one watch's filters (pass watch_id and the WHOLE new filter set, same keys as watch_intent); it gets a new watch_id and its next check is a fresh baseline, the old one stops. "delete": stop one watch for good. Use this when the user changes their mind instead of registering a second watch beside the first. Only the fingerprint that registered a watch can change it. Nothing personal is stored or accepted, as with watch_intent.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| filters | – | – | – |
| fingerprint | string | yes | – |
| watch_id | – | – | – |
No output schema declared.
No examples provided.
read_board Read an employer's board ~749
Read one employer's public job board live, whether or not the employer is in this index. Use it when the user names an employer this index does not carry (search_jobs returned the empty-result object, or the employer is outside AI infra, autonomous driving and embodied AI) and has, or can find on the employer's careers page, a board URL on a vendor this index knows how to read: Greenhouse (job-boards.greenhouse.io/<board>), Lever (jobs.lever.co/<site>), Ashby (jobs.ashbyhq.com/<board>), Moka (app.mokahr.com/apply/<org>/<siteId>), 北森 (<tenant>.zhiye.com), Workable (apply.workable.com/<subdomain>), SmartRecruiters (jobs.smartrecruiters.com/<company>) Workday (<account>.wd5.myworkdayjobs.com/<site>), Rippling (ats.rippling.com/<slug>/jobs) or Personio (<slug>.jobs.personio.de). Any sector. To keep the employer, add_employer puts the same board into the user's own index. What you get: the board's own postings with title, location, the board's own posting date and `days_open` where it reports one (`date_signal: not_reported_by_ats` otherwise), a direct apply link on the employer's own tenant, and a description excerpt that starts where the role does (company boilerplate skipped). Pass `ats_job_id` from a previous read to get that one posting with its whole `description`, when the user wants the job description itself read or summarised. What you do not get: skills, ghost_score, relist history or watches, which need repeated observation; and nothing is stored. If the employer turns out to be in the index the result says so and search_jobs is the richer source. Refused with ERR_UNSUPPORTED_BOARD, with the reason: a Feishu Hire / Lark portal (request signatures, an access control this index never bypasses), SuccessFactors, Taleo, iCIMS, LinkedIn, JobsDB or BOSS直聘. Tell the user to open that page themselves; never look for another way in. Politeness: one live read per board per 15 minutes per server process (a repeat within that window is answered from memory, `from_cac…
| Name | Type | Req | Description |
|---|---|---|---|
| ats_job_id | – | – | – |
| limit | integer | – | – |
| location | – | – | – |
| offset | integer | – | – |
| title | – | – | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
refresh_index Refresh one employer ~512
Re-crawl ONE employer's public ATS now. Takes about a minute. Throttled to 6h. The index is refreshed weekly, so `search_jobs` can be up to seven days behind and `check_watches` has nothing new to report until it moves. This is the manual nudge for the case that matters: the user is about to act on one employer and wants today's truth. Rules worth knowing before you call it: * ONE employer per call. A full crawl is 20+ minutes and no client will wait; a vague word like "robot" is refused with the list of candidates rather than fanned out into eleven live crawls. * At most one crawl per employer per 6 hours. A throttled call returns immediately with `refreshed: false`, `reason: "throttled"` and `last_refreshed_at` — no network request is made. That is not an error: it means the data you already hold is that fresh. * An employer we know but deliberately do not index (the Feishu-hosted ones, 蔚来 NIO, the ones whose own site has no readable job list, and 毫末智行 which has ceased operations; see search_jobs) returns `reason: "known_not_indexed"` with the same portal, reason and `employer_opt_in` the other tools give, never `unknown_company`. * Do NOT call this speculatively or in a loop. Every call hits somebody else's public endpoint. Search first; refresh only when the user needs today's state of one employer. Args: company: one employer — an id ("unitree") or any part of the name in either language ("宇树", "XPeng"). Ambiguous input is refused, not guessed. Returns: `refreshed` plus `last_refreshed_at` / `next_allowed_at`; when it did run, also jobs_new / jobs_updated / jobs_delisted / jobs_unchanged, `delisted` (job_id and title of the rows this crawl took down, first 20), `new` (the rows it added, first 20), `posting_dates_changed` (rows whose employer- reported posting date moved since the last crawl, was / now; say so and quote both) and `counts_note` on what the counts mean.
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | yes | – |
No output schema declared.
No examples provided.
remove_employer Remove an employer I added ~77
Take an employer the user added (add_employer) and its postings out of this machine's index. Employers in the public index cannot be removed this way (ERR_NOT_USER_ADDED). Args: company: the company_id add_employer returned, or any part of the employer's name.
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | yes | – |
No output schema declared.
No examples provided.
salary_benchmark Salary benchmark ~248
What employers themselves publish as pay for comparable live postings. Only ranges employers put on their own postings (most US postings carry one by law; most Chinese ones carry none). Never mixes currencies; annualises monthly pay. Low and high ends are reported separately as p25 / median / p75 (`annual_low`, `annual_high`), with `postings`, `employers` and `wide_ranges` (ranges spanning 2x or more). Under 20 postings there are no quantiles, only the count. Group by the level the title names (`seniority`, as in search_jobs) and the years the posting asks for (`years_min` / `years_max`, from the posting's own words), never by company grade. Quote `in_words`. Say these are published ranges, not offers or what anyone was paid, and never tell the user a posting "pays below market, skip it": give the numbers.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | yes | – |
| location | – | – | – |
| role_family | – | – | – |
| sector | – | – | – |
| seniority | – | – | – |
| title | – | – | – |
| years_max | – | – | – |
| years_min | – | – | – |
No output schema declared.
No examples provided.
search_jobs Search jobs ~3,977
Search the live job index by hard filters; returns ranked JobPosting[]. Pass `envelope: true` to get an object instead of a bare list: {results, matched (every row the filters match, before paging), returned, offset, has_more, next_offset, headline}. Use it whenever you will tell the user how many postings there are: a page of 10 is not the total, and an assistant once said "12 in all" when there were 15. The server does ONLY a hard filter plus a fixed ranking of match-quality × freshness — precise re-ranking is left to you, the client, which holds the user's context. Every result includes the five protocol fields (verified_at, source, ghost_score, response_sla_days, apply_channel) plus datePosted, days_open, remote_scope, eligible_regions, role_group and ghost_reason. Four fields are written for the person reading your answer (0.8.30): `seniority` is the level the title names (intern | junior | senior | staff | lead | manager | director | unknown; a product / project / account / policy / program manager is an individual contributor, so it is never "manager" on the word alone, while a title that names no level becomes "manager" when the posting's text plainly gives the role a team to run; the `seniority` filter's alias `ic` means every individual-contributor level (intern, junior, senior, staff, and unknown, because most titles name no level), so for a new graduate pass ["intern", "junior", "unknown"] and for an experienced IC ["senior", "staff", "unknown"]; listing levels leaves `unknown` out unless you name it. If you do not yet know whether the person leads people and how many years they have, ask before the first search rather than guessing the filter); `date_source` says whose date datePosted is (employer_ats | employer_self_reported | index_first_seen); `dates_in_words` is one sentence per language ("雇主发布日期 2026-09-23,在架 35 天;最近核验 2026-10-26…") to show verbatim instead of field names; `check_before_apply` lists what to confirm before applying, each item fr…
| Name | Type | Req | Description |
|---|---|---|---|
| collapse_role_group | boolean | – | – |
| company | – | – | – |
| currency | – | – | – |
| entry_level | boolean | – | – |
| envelope | boolean | – | – |
| limit | integer | – | – |
| location | – | – | – |
| min_salary | – | – | – |
| offset | integer | – | – |
| posted_within_days | – | – | – |
| remote | – | – | – |
| remote_scope | – | – | – |
| require_stated_salary | boolean | – | – |
| required_skills | – | – | – |
| role_family | – | – | – |
| sector | – | – | – |
| seniority | – | – | – |
| skills | – | – | – |
| title | – | – | – |
| title_exclude | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | – | yes | – |
No examples provided.
watch_intent Watch a job intent ~997
Register a standing intent so new matches can be pulled later. The caller supplies an anonymous fingerprint. For a user who has none yet, pass fingerprint="new": the server picks a random one and returns it (do not invent one yourself; models write the same "random" strings in every conversation and collide). A user's saved key from before is reused as is (12+ characters; a four-character tag collides with strangers). The client owns it; the server stores but can never recover it, so persist it client-side and pass the identical one to check_watches. Only the fingerprint and non-PII filter keys are stored — never a name, email, phone or résumé. Accepted filter keys mirror search_jobs: `skills` (ANY-overlap), `required_skills` (ALL/AND — use this to keep sales / solutions-architect roles out), `remote` (bool), `role_family` (e.g. "engineering"), `min_salary` (int), `company` (one employer, resolved at registration), `location` (substring of the location text, alias-aware like search_jobs: 广州 also reaches 广东·天河区 rows, Beijing reaches 北京市, "remote" reaches 远程), `title` (list of title substrings, ANY-of, synonym-expanded for HR terms like search_jobs — the way to watch for recruiting or other roles no skill tag names), `title_exclude` (title words to keep out on every pull, as in search_jobs: the user who wants "no 专家 roles" gets that enforced by the watch, not by you), `seniority` (list of levels or the aliases "ic" / "management", as in search_jobs, so a watch for an engineer never fires on a Senior Manager; `what_happens_next` says when titles naming no level are left out), `sector` (autonomous_driving / embodied_ai / ai_infra / finance / other, as in search_jobs: one watch for "robotics companies in Shenzhen" instead of one per employer), `entry_level` (true: only postings open to a new graduate, as in search_jobs), `posted_within_days` (only postings published in the last N days, as in search_jobs), `remote_scope` (worldwide / region_locked / country_locked / unk…
| Name | Type | Req | Description |
|---|---|---|---|
| filters | object | yes | – |
| fingerprint | string | yes | – |
No output schema declared.
No examples provided.
How do I install the OpenHire · 哨兵 MCP server?
OpenHire · 哨兵 runs locally as a PyPI package, launched with uvx openhire serve. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · openhire
claude mcp add gzchenhao-openhire -- uvx openhire serve
What is the OpenHire · 哨兵 MCP server?
OpenHire · 哨兵 is an MCP server listed in the public MCP registry as io.github.gzchenhao/openhire. Jobs with the employer's real posting date, from employers' own ATS. HR family. Résumé stays local. This page covers its PyPI package (openhire).
Is the OpenHire · 哨兵 MCP server safe to use?
OpenHire · 哨兵 scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 OpenHire · 哨兵 MCP server expose?
OpenHire · 哨兵 exposes 15 tools: search_jobs, get_company_info, get_job, watch_intent, refresh_index, and 10 more. Their descriptions and schemas cost roughly 11,051 tokens of context every time the server is loaded.
Is the OpenHire · 哨兵 MCP server still maintained?
OpenHire · 哨兵 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 licence is the OpenHire · 哨兵 MCP server under?
OpenHire · 哨兵 declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the OpenHire · 哨兵 MCP server?
VerifyMCP ran 15 checks on OpenHire · 哨兵, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about OpenHire · 哨兵: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.