{"id":"com.reqbeat/hiring-signals","slug":"com-reqbeat-hiring-signals","title":"Reqbeat Hiring Signals","description":"Find companies hiring for a role and geo, qualify them, and watch them for changes.","version":"1.1.4","publisher":{"kind":"domain","id":"reqbeat.com","label":"reqbeat.com","url":"https://reqbeat.com"},"website":"https://reqbeat.com/mcp/","repository":"https://github.com/reqbeat/mcp-server","remotes":[{"type":"streamable-http","url":"https://mcp.reqbeat.com/mcp","headers":[{"description":"Reqbeat plane API key. Required to call a tool: without it a call returns a signup link, not data.","isRequired":true,"isSecret":true,"name":"X-API-Key"}]}],"packages":[],"published":"2026-10-09","updated":"2026-10-09","status":"online","auth":"","latency_ms":1368,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"is_hiring","title":"Is this company hiring?","description":"WHEN an agent already holds a company and needs to qualify it -- the cheap gate before spending a richer call. LinkedIn-excluded (ATS tenants plus public job boards and aggregators) and freshness-floored. Takes the integer `company_id` from an earlier result, not a company name or domain. company_id=1234 -> is_hiring true, open_req_count 7, coverage_status \"ats_direct_hit\". company_id=5678 -> is_h","read_only":true},{"name":"get_open_reqs","title":"Open requisitions for a company","description":"The company's current active reqs, deduped across boards --\n    LinkedIn-excluded: ATS tenants plus public job boards and aggregators; each row's `boards` names its source.\n    Freshness-floored. Each row's `first_seen` is our first observation of\n    the req, not the employer's posting date; `source_posted_at` is the date\n    the source itself published, null when it gave none. `function` is a fu","read_only":true},{"name":"hiring_pulse","title":"Hiring velocity and direction","description":"One number set for one company: how many reqs it opened in the\n    last 30 days, a `velocity` ratio of that against the 30 days before\n    it, a `direction` of up / flat / down between the two, a surge flag,\n    and `momentum` -- postings published per week, a flow rather than a\n    stock. Use it to rank or score a company you already hold a\n    `company_id` for. Freshness is controlled by `max_ag","read_only":true},{"name":"who_is_hiring_for","title":"Find companies hiring for a role","description":"WHEN an agent needs to FIND the companies worth working -- the sourcing step, before it knows which companies exist. Reverse who's-hiring-for {title, geo} search: companies with active reqs matching `q`/`geo`/`since`, deduped by company, keyset-paginated via `cursor`. `q` is free text matched against the posting title, not an id; plurals and other inflections match, so \"backend engineers\" is the s","read_only":true},{"name":"search_jobs","title":"Search open roles","description":"Flat, role-granular job search -- the individual open roles across\n    companies matching `function` / `geo` (country) / `since`, one\n    row per logical req (each with its own `company_id` + `req_key`),\n    LinkedIn-excluded (ATS tenants plus public job boards and aggregators; each row's `board` names its source) +\n    freshness-floored. `since` filters on `first_seen`, our first\n    observation ","read_only":true},{"name":"get_role","title":"Get one role","description":"One open role's detail, addressed by the `company_id` + `req_key`\n    pair every `search_jobs` row already carries -- the follow-up call\n    for a role you hold an identifier for, instead of re-pulling the whole\n    company with `get_open_reqs`. Scoped exactly as `search_jobs` is:\n    LinkedIn-excluded (ATS tenants plus public job boards and aggregators) and freshness-floored. The body adds `raw_t","read_only":true},{"name":"find_qualified_reqs","title":"Find live roles matching an ICP","description":"WHEN an agent already knows its ideal customer profile and wants the\n    matching open roles as rows it can act on: several countries, an\n    industry, a headcount band and title keywords in ONE call, instead of a\n    search followed by a lookup per company. `criteria` takes up to three\n    groups -- `company` (country, industry, industry_terms, headcount_band,\n    company_kind), `req` (q, q_exclu","read_only":true},{"name":"pre_action_brief","title":"Pre-action brief for a company","description":"Everything an agent needs before acting on one company, in one\n    bounded round-trip instead of five: the hiring pulse, its top open\n    reqs deduped across boards, first-hire-by-function events,\n    hardest-to-fill (reposted) reqs and ATS-vendor migrations, pre-joined\n    and each section capped so the payload stays compact. Use it right\n    before writing outreach or a qualification note for a ","read_only":true},{"name":"get_changes","title":"Change feed since cursor","description":"The change feed, not a search: ledger events -- a req opened,\n    re-observed, reposted or closed -- with `event_seq > since`,\n    ascending, plus `next_cursor`. Replay with `next_cursor` instead of\n    polling or re-searching; an empty page bills nothing and one `change`\n    unit is metered per event returned. Filter by `company_id`, or by one\n    exact `event_type`. `limit` is bounded -- page wi","read_only":true},{"name":"find_company","title":"Find company by domain or name","description":"WHEN you hold a company's website or name but not the `company_id`\n    every company-scoped tool takes (`is_hiring`, `get_open_reqs`,\n    `hiring_pulse`, `pre_action_brief`, `watch_company`). Pass exactly one of\n    `domain` or `name`; both or neither is an error naming that rule.\n    `domain` takes a bare host or a full URL and matches exactly\n    ({\"domain\": \"https://www.stripe.com/jobs\"} -> the","read_only":true},{"name":"register_webhook","title":"Register a webhook endpoint","description":"Register the delivery target a watch fires to, and get back the\n    `webhook_endpoint_id` `watch_company` needs -- call this first if you\n    do not already hold one. Idempotent: registering the same `url` twice\n    returns the same id, so retrying is safe and never leaves you with two\n    endpoints. `secret` is optional; supply one to verify the\n    `X-Reqbeat-Signature` on delivered payloads, om","read_only":false},{"name":"watch_company","title":"Watch a company","description":"Subscribe to a company's hiring events on a registered webhook --\n    `webhook_endpoint_id` must belong to the same customer as the\n    authenticated key. Meters one `watch` unit.\n\n    `event_types` names which events fire it, at least one of: `opened` (a\n    req seen for the first time), `reobserved` (a known req seen again on a\n    later day), `reposted` (a req that came back after it was gone),","read_only":false},{"name":"list_watches","title":"List active watches","description":"WHEN you need to see what you are subscribed to -- before adding a\n    watch, or to find the `id` `cancel_watch` takes. Returns your live\n    watches newest first, cancelled ones excluded: {} -> {\"watches\": [{\"id\":\n    ..., \"company_id\": ..., \"event_types\": [...], \"webhook_endpoint_id\": ...,\n    \"status\": \"firing\", ...}]}. Each also reports its heartbeat --\n    `last_fired_at`, `fires_last_7d`, `f","read_only":true},{"name":"cancel_watch","title":"Cancel a watch","description":"WHEN a watch should stop firing. Takes the `id` `watch_company`\n    returned (or `list_watches` lists): {\"watch_id\": 42} -> {\"id\": 42,\n    \"canceled\": true}. Idempotent -- cancelling a watch you already cancelled\n    succeeds again. An id that is not one of your watches is an error,\n    identical whether it belongs to someone else or does not exist. Frees the\n    slot a free key's watch limit coun","read_only":false},{"name":"write_outcome","title":"Record a conversion outcome","description":"WHEN a company you reached through a signal converts -- a reply, a\n    meeting, a closed deal -- report it back. Takes the `company_id`, a short\n    `outcome` label of your choosing (e.g. \"meeting_booked\"), the\n    `observed_at` time it happened and, optionally, the `req_key` of the role\n    that prompted the outreach: {\"company_id\": 1234, \"outcome\":\n    \"meeting_booked\", \"observed_at\": \"2026-10-0","read_only":false},{"name":"get_skill_demand","title":"Market demand for one skill","description":"WHEN you need to know whether a skill or requirement is in demand --\n    how many distinct companies posted a role needing it in the last 90 days,\n    and where that puts it among all skills: {\"skill\": \"Python\"} -> {\"skill\":\n    \"Python\", \"company_count\": 41234, \"rank\": 3, \"total_skill_count\": 100465,\n    \"window_days\": 90, \"computed_at\": \"...\"}. Takes the skill as\n    `search_jobs` serves it in a","read_only":true},{"name":"top_skills","title":"Skills ranked by market demand","description":"WHEN you want the skills the market asks for most, rather than one\n    skill's number: the ranked list of skills by how many distinct companies\n    posted a role needing each in the last 90 days. {\"limit\": 3} ->\n    {\"skills\": [{\"rank\": 1, \"skill\": \"Communication\", \"company_count\": 52311},\n    ...], \"total_skill_count\": 100465, \"offset\": 0, \"has_more\": true,\n    \"window_days\": 90, \"computed_at\": \"","read_only":true}],"server_info":{"name":"hiring-signals","version":"1.1.4"},"category":"hr","tags":["automation","web-search"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-07-28","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/com-reqbeat-hiring-signals/"}