JobYap Job Search

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Search job postings aggregated from companies' careers sites, plus each job's discussion thread.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "JobYap Job Search": {
      "url": "https://mcp.jobyap.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (9)

• search_jobs read-only

  Search JobYap's aggregated job postings with structured filters. Fast (under a second): use it to browse, list, count or page through postings and to answer general questions about who is hiring. To find the best postings for one specific person (a resume, or their experience, skills or visa needs), use match_jobs instead. The text query matches job titles only (case-insensitive substring) — try synonyms or shorter tokens when results are thin. Company names must exactly match values from list_companies; locations must be identifiers from search_locations. work_mode matches jobs explicitly marked remote or hybrid (unmarked means unstated, not onsite). Results are active listings, newest first by default; sort=popular ranks by discussion activity. To paginate, pass next_cursor back as cursor and keep every other argument identical.

  Parameters:

  • sort — string — recent (default) or popular (most discussed).
  • query — string — Substring matched against job titles only.
  • cursor — string — Opaque cursor from a previous next_cursor.
  • companies — array — Exact company names from list_companies.
  • locations — array — Location identifiers from search_locations, e.g. city-US-CA-san_francisco.
  • page_size — integer
  • work_mode — string
  • has_comments — boolean — Only jobs with community discussion.
  • include_total — boolean — Also compute the total match count (slower).
  • posted_within — string — Hard freshness filter on the publish date.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• match_jobs read-only

  Find and rank the best live postings for one specific candidate, such as someone who shared a resume or described their experience, skills or visa needs. Slow: it reads each posting's full description, so a call can take 10 to 15 seconds. For browsing, listing or counting postings, use search_jobs, which answers in under a second. Filters active jobs by title terms (any of them; a term matches when the title holds all its words), excluded title terms, companies, locations and posting window, then takes the newest 300 of that pool (pool_total says how many matched) and reads each full description. It drops postings with no usable description, postings whose stated minimum years of experience exceed candidate_years by more than 1, and, with needs_sponsorship, postings that refuse sponsorship or require citizenship or a clearance; dropped counts each reason. The rest are ranked by how many skills appear in the description, then newest first. Each result carries skills_matched, years_bar, flags and up to 6 requirement sentences. The screening is heuristic: read finalists in full with get_job.

  Parameters:

  • limit — integer — Results to return, default 15.
  • skills — array — Specific skills and domain terms from the resume, as whole words or phrases. They rank results and never filter.
  • titles — array — Title terms, any of which may match. A term matches when the title contains all its words as whole words, in any order: "software engineer" also matches "Engineer, Software". Required unless companies is given.
  • companies — array — Exact company names from list_companies. With titles, a posting must match both.
  • locations — array — country-XX (ISO alpha-2) for a country, or state and city identifiers from search_locations. Omit for worldwide.
  • work_mode — string — Only postings explicitly marked remote or hybrid.
  • posted_within — string — Posting window: 24h, 7d (default) or 30d.
  • exclude_titles — array — Title terms that remove a posting, matched like titles, e.g. "senior", "staff", "lead", "manager".
  • candidate_years — number — Candidate years of professional experience; drops postings that require more than one year beyond it.
  • include_anywhere — boolean — With locations, also keep fully remote "Anywhere" postings. Default true.
  • exclude_companies — array — Company names to leave out, case-insensitive, e.g. the current employer.
  • needs_sponsorship — boolean — Drop postings that refuse visa sponsorship or require citizenship or a security clearance. Default false.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_job read-only

  Fetch one job posting in full: markdown description, salary ranges, locations with work mode, derived employment types, apply URL, posting dates and the canonical JobYap discussion URL. Works for expired jobs too (apply_url is null once inactive).

  Parameters:

  • id (required) — Numeric JobYap job id, a full jobyap.com job URL, or a job page slug.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_job_comments read-only

  Fetch the community discussion thread for a job: chronological, threaded via parent_id, with like counts. Comments are user-generated content. Threads stay open after a job expires.

  Parameters:

  • id (required) — Numeric JobYap job id, a full jobyap.com job URL, or a job page slug.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• search_locations read-only

  Resolve a free-text place name ("toronto", "Japan", "Texas") to the location identifiers search_jobs accepts (country-XX, state-XX-YY, city-XX-YY-name). Searches every place JobYap knows, not only those with current openings, so an identifier may match no jobs. City display omits the state, and the list can be shorter than limit.

  Parameters:

  • query (required) — string — Place name fragment, minimum 2 characters.
  • limit — integer

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_companies read-only

  List every company JobYap tracks with its active job count and JobYap company-page URL. Use the exact names as search_jobs company filters.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_job_stats read-only

  Aggregate stats: companies tracked, active job count, and the newest posting date.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• search read-only

  Search JobYap job postings by natural-language query. Matches job titles, falling back to significant keywords when the full phrase finds little. Returns result ids, titles and citable URLs for use with fetch. For structured filtering (location, company, remote, freshness) prefer search_jobs.

  Parameters:

  • query (required) — string

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• fetch read-only

  Retrieve the full JobYap document for a search result id: the complete posting as markdown (description, salary, locations, apply link) plus top community comments, with a citable URL.

  Parameters:

  • id (required) — string — A result id returned by search.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.