Productivity

resumebooster.work

Searches and retrieves live job postings from a board, checks whether listings are still open, and reports application-submission support.

1 endpoint15 known toolsFirst detected September 19, 2026Last detected September 19, 2026

ENDPOINT 1

https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp

No auth detected

MCP server metadata

Name: resumebooster-job-board
Version: 2026-09-04.8

Capabilities

toolspromptsresources

Server instructions

Live job search over employers' own hiring feeds, for an agent. Call board_stats first — it answers with no key and says what a key adds — then search_jobs; on a keyed session call key_status first: it says what the key may do, so no limit is learned by hitting it. A resumebooster.work/jobs?job=<id> link's id is the argument to get_job, fetch, check_apply_support and request_application. Four tiers. - No key: board_stats, search_jobs, search, fetch answer with no Authorization header at all — search capped at 10 rows, 25 calls a day per network address and 2000 a day across every unkeyed caller, each answer saying how many are left (search and fetch are search_jobs and get_job in the shape ChatGPT's research connector calls). - Free key, no account (https://resumebooster.work/data-api): 1,000 calls a day, every search filter, up to 60 rows, and every other read tool: get_job, get_jobs, check_jobs_open, check_apply_support, employer_hiring_record, employer_growth, key_status, debug_search. check_jobs_open takes 200 ids a call and get_jobs 10 — the quota counts calls, not ids. - Paid key, or a live Agent Pass: fit_resume — résumé fit scoring, as POST /v1/fit. - Account key (https://resumebooster.work/agents) with an Agent plan or a live Agent Pass (bought signed-in at https://resumebooster.work/agents/pass), plus a mandate set in Account: request_application, application_status. key_status shows a pass's time and applications left; the clock starts at the first call other than key_status. countUnavailable means the board refuses to guess a total; ignoredFilters names any filter it could not apply. This board watches postings come down and can say which employers take roles down and leave them down — employer_hiring_record and employer_growth carry that record per employer, with every unknown named as unknown. The guide: resumebooster://guide. Sign-in through this server is not switched on yet: a keyed tool called with no key answers in words, and the four unkeyed tools still work.

Known tools 15

search_jobs

Search the live job board (postings pulled directly from employers' own hiring systems, 30-day freshness cap; board_stats carries the live totals).

Inferred read-only

get_job

Full detail for one job id (from search_jobs), including the complete description text and when the employer's feed last confirmed it open.

Inferred read-only

get_jobs

Full detail for up to 10 job ids in ONE call — the shortlist form of get_job.

Inferred read-only

check_jobs_open

Are these postings still on the board?

Inferred read-only

check_apply_support

Whether the apply agent can submit an application for this job on the user's behalf, and what that requires.

Inferred read-only

request_application

Ask the board's apply agent to submit an application to this job on behalf of the key's owner.

Inferred read-only

application_status

Status of applications the key owner's agent has requested — queued, submitted, refused (with the refusing gate named), or failed.

Inferred read-only

fit_resume

Score a résumé against open jobs, for an agent holding a CV: reads the occupation out of resumeText (or uses `query` if given), searches the board for it, and scores up to 20 results 0-100 with the matched and missing terms per job.

Inferred read-only

board_stats

Live board statistics from cache (cheap to call): servable and tracked posting totals, the count of company job boards with open roles (boards, not employers — one employer can run several), the category set, freshness stamp.

Inferred read-only

employer_hiring_record

For each employer handle (companyToken, up to 20 per call), that employer's own record on this board: open_roles now, closed_90d (postings we watched come off this board in the last 90 days, re-lists excluded), superseded_90d (the re-lists, a floor), the two medians from the employer's own stated dates (lower bounds), tracking_days (how long we have watched THIS board, capped at 90) and feed_total (what its feed advertised at the last check).

Inferred read-only

employer_growth

Did this employer's board serve more roles than it did 7 days earlier?

Inferred read-only

key_status

What THIS key is and may do: tier, requests left this minute, calls left today (both including this call), whether fit_resume (and engine=ranked on the data API) answers on it, and whether the apply tools would — with any blocker named: account link, Agent plan or live pass, mandate, résumé on file.

Inferred read-only

debug_search

Explain WHY a search returns what it does — the board's own decision trace merged with the run's outcome.

Inferred read-only

search

An ALIAS of search_jobs in the fixed shape ChatGPT's deep-research and company-knowledge connectors call: one query string in, {results:[{id,title,url}]} out.

Inferred read-only

fetch

An ALIAS of get_job in the fixed shape ChatGPT's deep-research and company-knowledge connectors call: one id in (from search), {id,title,text,url,metadata} out.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.resumebooster-job-board]
url = "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "resumebooster-job-board": {
      "type": "http",
      "url": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: resumebooster-job-board
Remote MCP URL: https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "resumebooster-job-board": {
      "url": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "resumebooster-job-board": {
      "type": "http",
      "url": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "resumebooster-job-board",
  "transport": "streamable-http",
  "url": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for supabase.co was fetched 2026-08-24T06:42:13.245Z and is being refreshed.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.