Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "jobfeed": {
      "type": "http",
      "url": "https://findyourrolefirst.click/mcp",
      "headers": {
        "Authorization": "Bearer ${JOBFEED_TOKEN}"
      }
    }
  }
}

claude mcp add --transport http jobfeed https://findyourrolefirst.click/mcp --header "Authorization: Bearer ${JOBFEED_TOKEN}"

[mcp_servers.jobfeed]
url = "https://findyourrolefirst.click/mcp"
bearer_token_env_var = "JOBFEED_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jobfeed": {
      "type": "remote",
      "url": "https://findyourrolefirst.click/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:JOBFEED_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "jobfeed": {
      "type": "http",
      "url": "https://findyourrolefirst.click/mcp",
      "headers": {
        "Authorization": "Bearer ${JOBFEED_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=jobfeed&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vZmluZHlvdXJyb2xlZmlyc3QuY2xpY2svbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyICR7Sk9CRkVFRF9UT0tFTn0ifX0%3D"
}

{
  "servers": {
    "jobfeed": {
      "type": "http",
      "url": "https://findyourrolefirst.click/mcp",
      "headers": {
        "Authorization": "Bearer ${JOBFEED_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "jobfeed": {
      "httpUrl": "https://findyourrolefirst.click/mcp",
      "headers": {
        "Authorization": "Bearer ${JOBFEED_TOKEN}"
      }
    }
  }
}

extensions:
  "jobfeed":
    enabled: true
    name: "jobfeed"
    type: streamable_http
    uri: "https://findyourrolefirst.click/mcp"
    headers:
      "Authorization": "Bearer ${JOBFEED_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${JOBFEED_TOKEN}. The registry never accepts secret values.

Quality 86 / 100good

protocoln/a · weight 25

n/a
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)

authorization83 · weight 15

pass
auth.prmProtected Resource Metadata (RFC 9728) published
pass
auth.as_metadataauthorization server metadata reachable
warn
auth.cimdonly Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · 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
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,782 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability75 · weight 15

warn
stability.changes11 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.resolvableno npm or PyPI package

9 tools, about 2,782 tokens to load them all · tool set 1c33c2ab27a9 · tools last changed 2026-10-08 · checked 2026-10-19 10:52 UTC

Tool changes

2026-10-08count_jobschangedinput schema
2026-10-08search_jobschangedinput schema
2026-10-07get_apply_kitadded
Everything needed to help the person apply to one role themselves: the apply link, the application form's questions when the careers site publishes them (every Greenhouse role does), what we know about the role (experience asked for, level, pay, place, dates) and a short checklist. Draft answers and tailor the résumé with the person; they submit. This service never submits applications. Uses a credit like get_job if not unlocked.
2026-10-07get_new_for_meadded
Roles matching this person's saved preferences that were found since `since` (ISO time), newest found first. Leave since empty for the last 24 hours. Save checked_at from the reply and pass it as since next time: a daily or hourly check then never repeats a role. Uses credits like search_jobs for roles not unlocked this month.
2026-10-07get_my_profileadded
What this person told Find your role first they want: name, where they live, the roles (whole fields like "Software engineering" or titles), places, remote-only, experience, and what their résumés suggested. Use it to search on their behalf. Free.
2026-10-02count_jobschangedinput schema
2026-10-02search_jobschangedinput schema
2026-10-02count_jobschangedinput schema
2026-10-02search_jobschangedinput schema
2026-10-01count_jobschangedinput schema

Showing the latest 10. 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 95 / 100

provenance85

liveness99

freshness100

hygiene100

+repository +dns-namespace +website +reachable +uptime-98% +updated-11d-ago

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

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://findyourrolefirst.click/mcp` streamable-http	oauth2 AS: https://findyourrolefirst.click	yes	98%	298 ms	–	2026-10-19

Tools (9)

`count_jobs`read-only	Count the roles a search_jobs call would match, up to 1,000. Free: no jobs returned, no credits used. Use it to narrow a search (add a location, exclude words, posted_within_hours) before paying for results.
`get_apply_kit`read-only	Everything needed to help the person apply to one role themselves: the apply link, the application form's questions when the careers site publishes them (every Greenhouse role does), what we know about the role (experience asked for, level, pay, place, dates) and a short checklist. Draft answers and tailor the résumé with the person; they submit. This service never submits applications. Uses a credit like get_job if not unlocked.
`get_changes`read-only	Get new, updated, reopened, and closed jobs. Save next_cursor for the next check. Excludes baseline imports. History lasts 90 days; expired cursors need a fresh search.
`get_job`read-only	Get a job's metadata, original posting and application URLs, and latest known status. No job description is returned. Search already includes these fields; use this to refresh one record. Check closed_at and last_checked before applying. Reading the source page needs a separate web tool.
`get_my_profile`read-only	What this person told Find your role first they want: name, where they live, the roles (whole fields like "Software engineering" or titles), places, remote-only, experience, and what their résumés suggested. Use it to search on their behalf. Free.
`get_new_for_me`read-only	Roles matching this person's saved preferences that were found since `since` (ISO time), newest found first. Leave since empty for the last 24 hours. Save checked_at from the reply and pass it as since next time: a daily or hourly check then never repeats a role. Uses credits like search_jobs for roles not unlocked this month.
`get_usage`read-only	Check your remaining monthly allowance. This tool doesn't use your data allowance.
`list_my_jobs`read-only	List roles this account already unlocked, newest first. Free, and doesn't use credits.
`search_jobs`read-only	Find open jobs checked within 24 hours. Up to 20 results, newest posted first. query matches whole words in the title or company (e.g. "product manager", "quant", "ml engineer"). location takes a country ("United States", "UK", "India") or a city or state as written. exclude drops titles containing any of these words ("senior staff intern"). remote=true keeps remote roles only. posted_within_hours keeps recent postings. Call count_jobs first (free) to size a search before spending credits. Use published_since for source dates and discovered_since for new discoveries excluding baselines. Follow next_offset to paginate. No JD text is returned. experience keeps roles whose posting asks for these years of experience: any of "0-1", "1-3", "3-5", "5-8", "8+", "not_stated" (read, names none), "unchecked" (not read, or no text). Read from each posting; include not_stated and unchecked unless you mean to drop those roles. family="product_adjacent" finds product, product marketing, growth, customer success, forward deployed and business operations titles in one search; query narrows within it. roles takes several titles at once (["Product Manager", "Software Engineer"]) and matches any; locations likewise (["United States", "London", "Remote"]).

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "click.findyourrolefirst/jobfeed",
  "title": "Find your role first",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://findyourrolefirst.click/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "isRequired": true,
          "description": "Bearer YOUR_API_KEY. Create an agent key at https://findyourrolefirst.click/account"
        }
      ]
    }
  ],
  "version": "1.0.3",
  "repository": {
    "url": "https://github.com/yt6363/job-search-mcp",
    "source": "github"
  },
  "websiteUrl": "https://findyourrolefirst.click",
  "description": "New jobs from 15,000+ company career sites, newest first, for Claude Code, Codex and any agent."
}