Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "jobs": {
      "type": "http",
      "url": "https://mcp.jobyap.com/mcp"
    }
  }
}

claude mcp add --transport http jobs https://mcp.jobyap.com/mcp

[mcp_servers.jobs]
url = "https://mcp.jobyap.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jobs": {
      "type": "remote",
      "url": "https://mcp.jobyap.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "jobs": {
      "type": "http",
      "url": "https://mcp.jobyap.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=jobs&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmpvYnlhcC5jb20vbWNwIn0%3D"
}

{
  "servers": {
    "jobs": {
      "type": "http",
      "url": "https://mcp.jobyap.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "jobs": {
      "httpUrl": "https://mcp.jobyap.com/mcp"
    }
  }
}

extensions:
  "jobs":
    enabled: true
    name: "jobs"
    type: streamable_http
    uri: "https://mcp.jobyap.com/mcp"
    timeout: 300

Quality 86 / 100good

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene79 · weight 30

pass
tools.descriptionsevery tool has a description
warn
tools.description_length1 tools have descriptions over 1,024 characters, which crowds the context
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations9 of 9 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search_jobs (idempotentHint); get_job_comments (idempotentHint); search_locations (idempotentHint); …
pass
tools.token_costabout 2,374 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes4 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know [email protected]

9 tools, about 2,374 tokens to load them all · tool set 775c5adedd0e · tools last changed 2026-09-30 · checked 2026-10-20 20:14 UTC

Tool changes

2026-09-30search_locationschangeddescription
before
Resolve a free-text place name ("bay area", "Germany", "berlin") 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.
after · 86% of words in common
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.
2026-09-30match_jobschangeddescription
before
Shortlist, screen and rank live postings for one candidate in a single call. 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.
after · 74% of words in common
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.
2026-09-30search_jobschangeddescription
before
Search JobYap's aggregated job postings with structured filters. 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.
after · 71% of words in common
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.
2026-09-23match_jobsadded
Shortlist, screen and rank live postings for one candidate in a single call. 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.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 99 / 100

provenance100

liveness98

freshness100

hygiene100

+repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-96% +updated-19d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] npmthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.jobyap.com/mcp` streamable-http	none	yes	96%	399 ms	2026-07-28	2026-10-20

package	registry	version	runtime	secrets
`jobyap-mcp`	npm	1.1.0	–

Tools (9)

`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.
`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).
`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.
`get_job_stats`read-only	Aggregate stats: companies tracked, active job count, and the newest posting date.
`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.
`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.
`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.
`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.
`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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.jobyap/jobs",
  "title": "JobYap Job Search",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.jobyap.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.1.0",
  "packages": [
    {
      "version": "1.1.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "jobyap-mcp",
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org"
    }
  ],
  "repository": {
    "url": "https://github.com/jobyap/agent-skills",
    "source": "github"
  },
  "websiteUrl": "https://jobyap.com",
  "description": "Search job postings aggregated from companies' careers sites, plus each job's discussion thread."
}