Resume Booster Job Board

Official15 tools

by campbellaabbott-rgb · JavaScript

Job search over employers' own hiring systems. Search with no key; a free key opens every read tool.

work.resumebooster/jobs — Model Context Protocol (MCP) Server

Job search over employers’ own hiring systems. The server supports searching and fetching results without requiring a key: a “no key” path works for read tools, and a free key can open every read tool.

🛠️ Key Features

Job search across employers’ own hiring systems
Search and fetch answer with no key at all
Uses a board_stats check to report free call availability

🚀 Use Cases

Find job listings by querying employers’ hiring systems
Use board_stats to verify remaining free calls for the day

⚡ Developer Benefits

Fresh connections can make their first call from any host without needing a key
board_stats provides operational information about free call limits

⚠️ Limitations

The read tools without a key are dependent on free call availability, as indicated by board_stats

Captured live from the server via tools/list.

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). Returns compact job cards — including the board's own parsed pay (salaryMinAnnual/salaryMaxAnnual/salaryPeriod), experience band and minYears, so pay and seniority never have to be re-read out of prose — plus the board's honesty disclosures: exact totals when knowable (countUnavailable otherwise), filters it could not honour (ignoredFilters), words it read as filters (intentFilters), and spelling suggestions. Set agentReadyOnly=true to see only jobs the apply agent can submit to directly.

Parameters24

query	string	optional	Search terms. Supports exclusions: 'engineer -senior'.
location	string	optional	City/state/metro, e.g. 'texas', 'NYC', 'berlin'.
country	string	optional	ISO-2 codes, comma-separated, max 5. E.g. 'US,GB'.
remote	boolean	optional	Only remote-friendly roles.
workMode	string	optional	Comma list of: remote, hybrid, onsite.
employmentType	string	optional	Comma list of: full_time, part_time, contract, temporary, internship.
category	string	optional	Comma list of category slugs (see board_stats for the live set), max 3.
department	string	optional	Substring match on the employer's own department/team text.
companies	string	optional	Scope to specific employers: a comma list of companyToken values from job cards (or from the site's employer pages). An employer the board does not carry simply matches nothing; tokens the board drops are named in ignoredFilters.
experience	string	optional	Comma list of seniority bands the POSTING asks for: entry, mid, senior, expert. Rows whose band could not be read are excluded — use maxYears for the candidate's own side of the question.
maxAgeDays	number	optional	Only postings from the last N days (1-30).
postedAfter	string	optional	ISO-8601 instant; only postings the EMPLOYER dated after it. Undated rows fall out of this window (unlike maxAgeDays, which falls back to when the board first saw a posting), so this is the strict form of 'new'.
salaryMin	number	optional	Annual USD-equivalent salary floor. Note: only ~13% of postings state pay.
salaryMax	number	optional	Annual USD-equivalent salary ceiling.
includeUnstatedPay	boolean	optional	WIDENS an active salaryMin/salaryMax band to also admit postings that state no pay at all. Inert with no band set (unpriced rows are already included). The response says salaryStatedOnly when a band is narrowing without it.
hasStatedPay	boolean	optional	Only postings that state a salary (excludes the ~87% that don't).
payBasis	string	optional	Restrict to hourly or salaried pay.
maxYears	number	optional	Only roles asking for at most N years of experience.
vendor	string	optional	Comma list of hiring-system vendors (greenhouse, lever, ashby, …), max 8.
excludeAgencies	boolean	optional	Hide postings from staffing/recruiting agencies (their job cards carry agency:true). Agencies are served by default; this is an opt-in narrowing.
agentReadyOnly	boolean	optional	Only jobs the apply agent can submit to on the user's behalf.
sort	string	optional	Default relevance.
limit	number	optional	Rows per page, 1-60. Default 20.
offset	number	optional	Paging offset — pass back the previous response's nextOffset.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search terms. Supports exclusions: 'engineer -senior'."
    },
    "location": {
      "type": "string",
      "description": "City/state/metro, e.g. 'texas', 'NYC', 'berlin'."
    },
    "country": {
      "type": "string",
      "description": "ISO-2 codes, comma-separated, max 5. E.g. 'US,GB'."
    },
    "remote": {
      "type": "boolean",
      "description": "Only remote-friendly roles."
    },
    "workMode": {
      "type": "string",
      "description": "Comma list of: remote, hybrid, onsite."
    },
    "employmentType": {
      "type": "string",
      "description": "Comma list of: full_time, part_time, contract, temporary, internship."
    },
    "category": {
      "type": "string",
      "description": "Comma list of category slugs (see board_stats for the live set), max 3."
    },
    "department": {
      "type": "string",
      "description": "Substring match on the employer's own department/team text."
    },
    "companies": {
      "type": "string",
      "description": "Scope to specific employers: a comma list of companyToken values from job cards (or from the site's employer pages). An employer the board does not carry simply matches nothing; tokens the board drops are named in ignoredFilters."
    },
    "experience": {
      "type": "string",
      "description": "Comma list of seniority bands the POSTING asks for: entry, mid, senior, expert. Rows whose band could not be read are excluded — use maxYears for the candidate's own side of the question."
    },
    "maxAgeDays": {
      "type": "number",
      "description": "Only postings from the last N days (1-30)."
    },
    "postedAfter": {
      "type": "string",
      "description": "ISO-8601 instant; only postings the EMPLOYER dated after it. Undated rows fall out of this window (unlike maxAgeDays, which falls back to when the board first saw a posting), so this is the strict form of 'new'."
    },
    "salaryMin": {
      "type": "number",
      "description": "Annual USD-equivalent salary floor. Note: only ~13% of postings state pay."
    },
    "salaryMax": {
      "type": "number",
      "description": "Annual USD-equivalent salary ceiling."
    },
    "includeUnstatedPay": {
      "type": "boolean",
      "description": "WIDENS an active salaryMin/salaryMax band to also admit postings that state no pay at all. Inert with no band set (unpriced rows are already included). The response says salaryStatedOnly when a band is narrowing without it."
    },
    "hasStatedPay": {
      "type": "boolean",
      "description": "Only postings that state a salary (excludes the ~87% that don't)."
    },
    "payBasis": {
      "type": "string",
      "enum": [
        "hourly",
        "salaried"
      ],
      "description": "Restrict to hourly or salaried pay."
    },
    "maxYears": {
      "type": "number",
      "description": "Only roles asking for at most N years of experience."
    },
    "vendor": {
      "type": "string",
      "description": "Comma list of hiring-system vendors (greenhouse, lever, ashby, …), max 8."
    },
    "excludeAgencies": {
      "type": "boolean",
      "description": "Hide postings from staffing/recruiting agencies (their job cards carry agency:true). Agencies are served by default; this is an opt-in narrowing."
    },
    "agentReadyOnly": {
      "type": "boolean",
      "description": "Only jobs the apply agent can submit to on the user's behalf."
    },
    "sort": {
      "type": "string",
      "enum": [
        "relevance",
        "newest",
        "salary"
      ],
      "description": "Default relevance."
    },
    "limit": {
      "type": "number",
      "description": "Rows per page, 1-60. Default 20."
    },
    "offset": {
      "type": "number",
      "description": "Paging offset — pass back the previous response's nextOffset."
    }
  }
}

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. A resumebooster.work/jobs?job=<id> link's id is this argument (and fetch's, check_apply_support's and request_application's). For several ids at once, use get_jobs — it costs ONE call against the daily quota instead of one per posting. Needs a key or a sign-in. With neither, call fetch with the same id.

Parameters1

string

required

The job id, e.g. 'greenhouse:acme:12345'.

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "The job id, e.g. 'greenhouse:acme:12345'."
    }
  },
  "required": [
    "id"
  ]
}

get_jobs

Full detail for up to 10 job ids in ONE call — the shortlist form of get_job. Each id answers with a card plus its description; ids that closed, aged out or were never on this board come back in `unavailable` with the reason named, so one dead id never costs you the other nine. Set includeDescription=false for cards and freshness only (much smaller, and no vendor fetch). Needs a key or a sign-in.

Parameters2

ids	array	required	Job ids from search_jobs. Up to 10 per call — each one is a separate detail read that may fetch the employer's page.
includeDescription	boolean	optional	Default true. Descriptions are capped at 8,000 characters here; call get_job for the whole text of one.

Raw schema

{
  "type": "object",
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Job ids from search_jobs. Up to 10 per call — each one is a separate detail read that may fetch the employer's page."
    },
    "includeDescription": {
      "type": "boolean",
      "description": "Default true. Descriptions are capped at 8,000 characters here; call get_job for the whole text of one."
    }
  },
  "required": [
    "ids"
  ]
}

check_jobs_open

Are these postings still on the board? Answers up to 200 ids in one call — the tool for re-verifying a saved shortlist before acting on it, instead of spending a metered get_job per posting. Returns open:{id:boolean} plus the closed ids, and names the basis of the answer: it reads the board's index (a closed posting is one the employer's feed stopped listing), not the employer's site at this instant, and it is a weaker test than get_job's — read `basis` before reporting a posting as live to a person. Needs a key or a sign-in.

Parameters1

ids

array

required

Job ids from search_jobs. Up to 200 per call; anything past that is named in notChecked rather than silently dropped.

Raw schema

{
  "type": "object",
  "properties": {
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 200,
      "description": "Job ids from search_jobs. Up to 200 per call; anything past that is named in notChecked rather than silently dropped."
    }
  },
  "required": [
    "ids"
  ]
}

check_apply_support

Whether the apply agent can submit an application for this job on the user's behalf, and what that requires. Jobs on non-supported systems still return their direct applyUrl for the human to use. For whether THIS KEY may apply at all, call key_status — this tool answers about the job, not the key. Needs a key or a sign-in.

Parameters1

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    }
  },
  "required": [
    "id"
  ]
}

request_application

Ask the board's apply agent to submit an application to this job on behalf of the key's owner. Needs an account key (mint one at https://resumebooster.work/agents), an active Agent plan OR a live Agent Pass (bought signed-in at https://resumebooster.work/agents/pass), and a mandate set in Account — call key_status first: it says which of the three is missing, and on a pass how many applications and how much time are left. Every application passes the same gates as the signed-in flow, including the honesty classifier: answers are drawn from the owner's own profile and never invented. Ask the person for a yes on this specific job id before calling. Needs a key or a sign-in.

Parameters2

jobId	string	required	The job id from search_jobs.
note	string	optional	Optional note stored with the request (not sent to the employer).

Raw schema

{
  "type": "object",
  "properties": {
    "jobId": {
      "type": "string",
      "description": "The job id from search_jobs."
    },
    "note": {
      "type": "string",
      "description": "Optional note stored with the request (not sent to the employer)."
    }
  },
  "required": [
    "jobId"
  ]
}

application_status

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

Parameters1

limit

number

optional

Most recent N, default 20, max 50.

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Most recent N, default 20, max 50."
    }
  }
}

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. PAID — needs a paid API key, exactly like POST /v1/fit on the data API, or a live Agent Pass on the key's account; a free key gets an in-band refusal naming where to upgrade. A null fit means the posting has no stored description to score. Returns the terms it read from the CV so the agent can pick a different one and call again with `query`. Needs a key or a sign-in.

Parameters6

resumeText	string	required	The candidate's résumé as plain text (100+ characters).
query	string	optional	Optional job title to search instead of the one read from the résumé.
location	string	optional
country	string	optional
remote	boolean	optional
limit	integer	optional	Jobs to score, 1-20 (default 20).

Raw schema

{
  "type": "object",
  "properties": {
    "resumeText": {
      "type": "string",
      "description": "The candidate's résumé as plain text (100+ characters)."
    },
    "query": {
      "type": "string",
      "description": "Optional job title to search instead of the one read from the résumé."
    },
    "location": {
      "type": "string"
    },
    "country": {
      "type": "string"
    },
    "remote": {
      "type": "boolean"
    },
    "limit": {
      "type": "integer",
      "description": "Jobs to score, 1-20 (default 20)."
    }
  },
  "required": [
    "resumeText"
  ]
}

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. Answers with no key too, with a withKey block saying what a free key adds.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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). A takedown is not a hire — a filled role, a cancelled one and a withdrawn one look identical from here — and it is a record of one BOARD, never summed across an employer's boards, never a headcount. A board with no closure observed answers record:'unknown' with the reason, never a verdict about the employer: on a board bigger than one visit can read, no closure is observable to us until we complete a provable full pass and then watch a role go after it, so silence there is about our instrument. Every row carries its basis. Every row also carries layoff_filing — the newest layoff filing joined to that employer by a hand-curated alias or an exact multi-token name match, a US state WARN notice or an SEC 8-K Item 2.05 disclosure, printed as a filing (filer verbatim, its dates with their bases, count, state or form, link), read hourly from SEC EDGAR and nightly from state notices, null when none qualifies within 90 days, and no part of record or any verdict; layoff_basis on the response says what it is and is not. Pair with employer_growth for the other half of what the site calls "Actively hiring". Needs a key or a sign-in.

Parameters1

companyTokens

array

required

companyToken values from job cards or search_jobs (a vendor tenant, e.g. 'acme' or 'gici~wd5~Careers'). Up to 20; more is refused with the count named.

Raw schema

{
  "type": "object",
  "properties": {
    "companyTokens": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 20,
      "description": "companyToken values from job cards or search_jobs (a vendor tenant, e.g. 'acme' or 'gici~wd5~Careers'). Up to 20; more is refused with the count named."
    }
  },
  "required": [
    "companyTokens"
  ]
}

employer_growth

Did this employer's board serve more roles than it did 7 days earlier? One row per companyToken (up to 20 per call), judged by the board itself from our own daily observation and passed through untouched: grew, no-growth, or unknown — and unknown ALWAYS carries unknown_reason (a feed bigger than one visit can read, a board too new or too small for a rate, a gap in our own series, a pool that was replaced rather than grown…): an unknown is a reading we could not take, never a no. The bars the verdict uses: at least 10 roles served at the window's start; then BOTH at least 4 more roles AND at least 25% more, on a board tracked for at least 21 days, with every read in the window whole. Per BOARD (a vendor tenant), never summed across an employer's boards; more roles served is roles opened net of roles that came down — not a headcount and not a hire. This tool never ranks employers, and no list of growing employers exists here or anywhere on the board. Needs a key or a sign-in.

Parameters1

companyTokens

array

required

companyToken values from job cards or search_jobs. Up to 20; more is refused with the count named.

Raw schema

{
  "type": "object",
  "properties": {
    "companyTokens": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 20,
      "description": "companyToken values from job cards or search_jobs. Up to 20; more is refused with the count named."
    }
  },
  "required": [
    "companyTokens"
  ]
}

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. On an Agent Pass: when the clock ends and how many applications are left (a pass starts at the first call other than this one). Call it first in a keyed session, and after any 'quota' or 'rate' refusal. Needs a key or a sign-in.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

debug_search

Explain WHY a search returns what it does — the board's own decision trace merged with the run's outcome. Shows the parsed query (terms, exclusions, intent-lifts, alias expansions), which filters were applied vs IGNORED and why, the route and retriever chosen, the ranking regime (ranked/ring-merged/deep-page and the seam), plus the real run's route, timings, count basis and any fallback. Use this when a search returns surprising, empty, or mis-ranked results — it turns 'why?' into one call. Takes the SAME arguments as search_jobs. Needs a key or a sign-in.

Parameters24

query	string	optional	Search terms. Supports exclusions: 'engineer -senior'.
location	string	optional	City/state/metro, e.g. 'texas', 'NYC', 'berlin'.
country	string	optional	ISO-2 codes, comma-separated, max 5. E.g. 'US,GB'.
remote	boolean	optional	Only remote-friendly roles.
workMode	string	optional	Comma list of: remote, hybrid, onsite.
employmentType	string	optional	Comma list of: full_time, part_time, contract, temporary, internship.
category	string	optional	Comma list of category slugs (see board_stats for the live set), max 3.
department	string	optional	Substring match on the employer's own department/team text.
companies	string	optional	Scope to specific employers: a comma list of companyToken values from job cards (or from the site's employer pages). An employer the board does not carry simply matches nothing; tokens the board drops are named in ignoredFilters.
experience	string	optional	Comma list of seniority bands the POSTING asks for: entry, mid, senior, expert. Rows whose band could not be read are excluded — use maxYears for the candidate's own side of the question.
maxAgeDays	number	optional	Only postings from the last N days (1-30).
postedAfter	string	optional	ISO-8601 instant; only postings the EMPLOYER dated after it. Undated rows fall out of this window (unlike maxAgeDays, which falls back to when the board first saw a posting), so this is the strict form of 'new'.
salaryMin	number	optional	Annual USD-equivalent salary floor. Note: only ~13% of postings state pay.
salaryMax	number	optional	Annual USD-equivalent salary ceiling.
includeUnstatedPay	boolean	optional	WIDENS an active salaryMin/salaryMax band to also admit postings that state no pay at all. Inert with no band set (unpriced rows are already included). The response says salaryStatedOnly when a band is narrowing without it.
hasStatedPay	boolean	optional	Only postings that state a salary (excludes the ~87% that don't).
payBasis	string	optional	Restrict to hourly or salaried pay.
maxYears	number	optional	Only roles asking for at most N years of experience.
vendor	string	optional	Comma list of hiring-system vendors (greenhouse, lever, ashby, …), max 8.
excludeAgencies	boolean	optional	Hide postings from staffing/recruiting agencies (their job cards carry agency:true). Agencies are served by default; this is an opt-in narrowing.
agentReadyOnly	boolean	optional	Only jobs the apply agent can submit to on the user's behalf.
sort	string	optional	Default relevance.
limit	number	optional	Rows per page, 1-60. Default 20.
offset	number	optional	Paging offset — pass back the previous response's nextOffset.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search terms. Supports exclusions: 'engineer -senior'."
    },
    "location": {
      "type": "string",
      "description": "City/state/metro, e.g. 'texas', 'NYC', 'berlin'."
    },
    "country": {
      "type": "string",
      "description": "ISO-2 codes, comma-separated, max 5. E.g. 'US,GB'."
    },
    "remote": {
      "type": "boolean",
      "description": "Only remote-friendly roles."
    },
    "workMode": {
      "type": "string",
      "description": "Comma list of: remote, hybrid, onsite."
    },
    "employmentType": {
      "type": "string",
      "description": "Comma list of: full_time, part_time, contract, temporary, internship."
    },
    "category": {
      "type": "string",
      "description": "Comma list of category slugs (see board_stats for the live set), max 3."
    },
    "department": {
      "type": "string",
      "description": "Substring match on the employer's own department/team text."
    },
    "companies": {
      "type": "string",
      "description": "Scope to specific employers: a comma list of companyToken values from job cards (or from the site's employer pages). An employer the board does not carry simply matches nothing; tokens the board drops are named in ignoredFilters."
    },
    "experience": {
      "type": "string",
      "description": "Comma list of seniority bands the POSTING asks for: entry, mid, senior, expert. Rows whose band could not be read are excluded — use maxYears for the candidate's own side of the question."
    },
    "maxAgeDays": {
      "type": "number",
      "description": "Only postings from the last N days (1-30)."
    },
    "postedAfter": {
      "type": "string",
      "description": "ISO-8601 instant; only postings the EMPLOYER dated after it. Undated rows fall out of this window (unlike maxAgeDays, which falls back to when the board first saw a posting), so this is the strict form of 'new'."
    },
    "salaryMin": {
      "type": "number",
      "description": "Annual USD-equivalent salary floor. Note: only ~13% of postings state pay."
    },
    "salaryMax": {
      "type": "number",
      "description": "Annual USD-equivalent salary ceiling."
    },
    "includeUnstatedPay": {
      "type": "boolean",
      "description": "WIDENS an active salaryMin/salaryMax band to also admit postings that state no pay at all. Inert with no band set (unpriced rows are already included). The response says salaryStatedOnly when a band is narrowing without it."
    },
    "hasStatedPay": {
      "type": "boolean",
      "description": "Only postings that state a salary (excludes the ~87% that don't)."
    },
    "payBasis": {
      "type": "string",
      "enum": [
        "hourly",
        "salaried"
      ],
      "description": "Restrict to hourly or salaried pay."
    },
    "maxYears": {
      "type": "number",
      "description": "Only roles asking for at most N years of experience."
    },
    "vendor": {
      "type": "string",
      "description": "Comma list of hiring-system vendors (greenhouse, lever, ashby, …), max 8."
    },
    "excludeAgencies": {
      "type": "boolean",
      "description": "Hide postings from staffing/recruiting agencies (their job cards carry agency:true). Agencies are served by default; this is an opt-in narrowing."
    },
    "agentReadyOnly": {
      "type": "boolean",
      "description": "Only jobs the apply agent can submit to on the user's behalf."
    },
    "sort": {
      "type": "string",
      "enum": [
        "relevance",
        "newest",
        "salary"
      ],
      "description": "Default relevance."
    },
    "limit": {
      "type": "number",
      "description": "Rows per page, 1-60. Default 20."
    },
    "offset": {
      "type": "number",
      "description": "Paging offset — pass back the previous response's nextOffset."
    }
  }
}

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. Every result's id is the job id fetch and every other tool take; url is the employer's own apply page when the board holds one, else the posting's page on the site. Same board, same ranking, same limit as an unkeyed search_jobs (10 rows); the disclosures ride beside the results. Any other client should call search_jobs, which takes every filter.

Parameters1

query

string

required

Free text — title, skills, a place, exclusions with a leading minus.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free text — title, skills, a place, exclusions with a leading minus."
    }
  },
  "required": [
    "query"
  ]
}

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. text is the posting's full description; metadata carries the job card's structured fields (pay, experience, location, workMode, postedAt, companyToken, agentReady). A dead id answers with what the board knows — a watched closure, an aged-out stub, or not found — in text and metadata, never a stale card. Any other client should call get_job.

Parameters1

string

required

A job id from search.

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "A job id from search."
    }
  },
  "required": [
    "id"
  ]
}

README.md24 KBView on GitHub

Resume Booster Job Board — MCP server

Job search over employers' own hiring systems. Search with no key; a free key opens every read tool. board_stats, search_jobs, search and fetch answer with no key at all, so a fresh connection works on its first call from any host.

Verify: ask your agent to call board_stats. It answers with no key and says how many free calls are left today.

Server address: https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp — this address is on Supabase, the company that hosts our server; it is ours. Paste it exactly as it is (do not add /mcp). It is a plain web address your agent talks to (MCP over Streamable HTTP, one POST per message, no session to keep); there is nothing to install.
Tools: 15 — search_jobs, get_job, get_jobs, check_jobs_open, check_apply_support, board_stats, employer_hiring_record, employer_growth, key_status, debug_search, search, fetch, fit_resume, request_application, application_status
The how-to, per app, with a Test the server button: https://resumebooster.work/agents
Free key: https://resumebooster.work/data-api
One server, four names: resumebooster-job-board is what initialize answers, resumebooster is the install name in every block below, Resume Booster is the name you type into Claude's or ChatGPT's own dialog, and work.resumebooster/jobs is the name reserved for the MCP Registry (not published yet).

A https://resumebooster.work/jobs?job=<id> link's id is the argument get_job, fetch, check_apply_support and request_application take.

Claude, Claude Desktop and ChatGPT have no field for a key. They sign you in instead — but only while the server's sign-in service is switched on. When it is off, a tool that needs your account answers in words (no Connect card), and board_stats, search_jobs, search and fetch still answer. Today's state: press Test the server on https://resumebooster.work/agents, or run

curl -s -X POST https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp -H 'content-type: application/json' -H 'mcp-protocol-version: 2025-06-18' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"0"}}}' | jq '.result._meta["work.resumebooster/sign-in"].state'

which prints "on", "off" or "unknown" — the same word the page shows (the server reads the sign-in service's own metadata at https://bwhdazbotpblihdxcmho.supabase.co/.well-known/oauth-authorization-server/auth/v1 and caches the answer briefly).

Tiers

Tier	Tools	What opens it
Unkeyed	`board_stats`, `search_jobs`, `search`, `fetch`	Nothing. 25 calls a day per network address, 2000 a day across every unkeyed caller, a search is one page of 10 rows.
Free key	`get_job`, `get_jobs`, `check_jobs_open`, `check_apply_support`, `employer_hiring_record`, `employer_growth`, `key_status`, `debug_search` (and the unkeyed tools at a higher cap)	A free key from https://resumebooster.work/data-api — 1000 calls a day.
Paid or pass	`fit_resume`	The paid API tier, or a live pass on the key's account (https://resumebooster.work/agents/pass).
Apply	`request_application`, `application_status`	A key linked to an account with an Agent plan or a live pass, and a mandate — see `key_status`.

The unkeyed allowance is 25 free calls a day per network address — an office, a home connection or a chat service's own servers count as one address, so from Claude or ChatGPT the number left can start lower because other people share it.

Install

Pick your app. Every block but Zed's works with no key on its first call (Zed asks you to sign in when no key is set — its section says what to do); the keyed variant under a block is optional.

Claude (claude.ai, Claude Desktop, Claude on your phone)

In Claude, open Customize, then Connectors.
Click Add custom connector. On a Team or Enterprise plan there is no such button: an owner adds the connector under Organization settings > Connectors (Add, then Custom; if it asks for the connector type, Web), and you then find it under Customize > Connectors with the "Custom" label and click Connect.
If it asks for a Name, type Resume Booster.
Paste this address into MCP server URL: https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp — this address is on Supabase, the company that hosts our server; it is ours. Paste it exactly as it is.
If Claude asks about Authentication, choose Sign in when needed. If it asks about OAuth client, choose Register automatically. Claude may already show these as "Detected" — leave them. Do not choose No sign-in: Claude cannot change that later, so the tools that need your account would stay off until you remove the connector and add it again.
Click Add.
In a chat, click +, open Connectors, and switch Resume Booster on.
Ask Claude: Using Resume Booster, call board_stats and tell me how many jobs are open right now.

When sign-in is on — the first time Claude needs your account — to open a posting in full, to check a shortlist, or to apply — a Connect card appears in the chat. Click it, sign in to Resume Booster, press Allow, and Claude continues where it stopped.

How you know it worked: Under + → Connectors, Resume Booster is on. Ask "call board_stats": the answer names the number of open postings and a note that reads "unkeyed: N of 25 anonymous calls left today".

ChatGPT (developer mode)

In ChatGPT, open Settings, choose Security and login, and turn on Developer mode. If you do not see it, your account or workspace does not allow it yet.
Go to chatgpt.com/plugins and click the + button.
Type a name — Resume Booster — and a description — Live job board: search real openings from employers' own hiring systems.
Under Connection, paste this address as the MCP server URL: https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp. Paste it exactly as it is — do not add /mcp at the end. The address is on Supabase, the company that hosts our server; it is ours.
Create the connection, and check the list of tools it found — there should be 15.
Start a new chat and add Resume Booster from the tools menu.
Ask: Search Resume Booster for nurse jobs in Texas and show me the first ten.

When sign-in is on — if a tool needs your account, ChatGPT shows its sign-in for Resume Booster; sign in and press Allow.

How you know it worked: Ask it to search for "nurse in Texas": 10 results with ids come back. ChatGPT's own search uses search and fetch — 10 results per search and the full text of any result — with no sign-in.

Claude Code

Copy this line and run it in your terminal (--scope user makes it available in every folder, not just this one): claude mcp add --transport http --scope user resumebooster https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp
Start claude and type /mcp — resumebooster is listed as connected.
Ask: call board_stats — the answer names the number of open postings and says how many free calls are left today.

With a free key, for every project:

export RESUMEBOOSTER_KEY=<paste your key here>
claude mcp add --transport http --scope user resumebooster https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp --header "Authorization: Bearer $RESUMEBOOSTER_KEY"

Or clone this repository: its .mcp.json is a project-scope server, so Claude Code asks once to approve it and you are connected. As a plugin (adds the /resumebooster:setup and /resumebooster:find-jobs skills):

text

/plugin marketplace add campbellaabbott-rgb/resumebooster-mcp
/plugin install resumebooster@resumebooster

The .mcp.json in this repo reads the key from the environment: ${RESUMEBOOSTER_KEY:-} expands to the key when RESUMEBOOSTER_KEY is set and to nothing otherwise, and the server answers an empty header as the unkeyed tier — so the same file works with a key and without one. The keyless variant, if you would rather no header be sent at all:

json

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

When sign-in is on — without a key, the first tool that needs your account makes /mcp show ! Needs authentication; type /mcp and sign in in the browser (Claude Code 2.1.186 or newer can also run claude mcp login resumebooster).

How you know it worked: /mcp lists resumebooster as connected; "call board_stats" answers with the count and the unkeyed note; with a key, "call key_status" names your tier and calls left.

Cursor

Paste this link into your browser's address bar (GitHub does not make it clickable) — Cursor opens and asks you to confirm the server; the link holds only the address, never a key: cursor://anysphere.cursor-deeplink/mcp/install?name=resumebooster&config=eyJ1cmwiOiJodHRwczovL2J3aGRhemJvdHBibGloZHhjbWhvLnN1cGFiYXNlLmNvL2Z1bmN0aW9ucy92MS9hZ2VudC1tY3AifQ==
Or paste the block below into ~/.cursor/mcp.json.
In Cursor's chat, ask: call board_stats.

json

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

With a free key, the same file names the variable and Cursor fills it in (${env:RESUMEBOOSTER_KEY} is resolved in headers), so the key never sits in the file:

export RESUMEBOOSTER_KEY=<paste your key here>

json

{
  "mcpServers": {
    "resumebooster": {
      "url": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp",
      "headers": {
        "Authorization": "Bearer ${env:RESUMEBOOSTER_KEY}"
      }
    }
  }
}

How you know it worked: Ask the chat "call board_stats" — the count and the unkeyed note come back.

VS Code

Paste this link into your browser's address bar — VS Code asks you to confirm: vscode:mcp/install?%7B%22name%22%3A%22resumebooster%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fbwhdazbotpblihdxcmho.supabase.co%2Ffunctions%2Fv1%2Fagent-mcp%22%7D (Insiders: vscode-insiders:mcp/install?%7B%22name%22%3A%22resumebooster%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fbwhdazbotpblihdxcmho.supabase.co%2Ffunctions%2Fv1%2Fagent-mcp%22%7D).
Or paste the block below into .vscode/mcp.json. When the server starts, VS Code asks for the key; leave it empty to use the tools that need no key (VS Code's own document does not say what an empty answer does — if the server does not start, use the link in step 1 instead).
In the chat, ask: call board_stats.

json

{
  "inputs": [
    {
      "id": "resumebooster-key",
      "type": "promptString",
      "description": "Resume Booster Job Board API key (free at https://resumebooster.work/data-api); leave empty for the unkeyed tools",
      "password": true
    }
  ],
  "servers": {
    "resumebooster": {
      "type": "http",
      "url": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp",
      "headers": {
        "Authorization": "Bearer ${input:resumebooster-key}"
      }
    }
  }
}

— the same link as step 1, made clickable through vscode.dev's redirect (a convenience GitHub needs; VS Code's docs describe only the vscode: form).

How you know it worked: If you used the mcp.json block, VS Code asks for the key at start — leave it empty (the link in step 1 declares no key, so it asks nothing). Either way, ask the chat "call board_stats" — the count and the unkeyed note come back.

More… (Gemini CLI, Codex CLI, Cline, Zed, Windsurf, anything else)

Pick your app below — each has its own block. Anything else that speaks MCP works too: it is one plain web address, and Any client / curl at the end shows the first message.
Then ask your agent to call board_stats.

When sign-in is on — without a key, a tool that needs your account answers a sign-in challenge (HTTP 401); a client that supports sign-in opens it, and a client that does not needs a free key.

How you know it worked: The initialize answer's serverInfo.name is resumebooster-job-board; the Test the server button on https://resumebooster.work/agents runs this for you.

Gemini CLI

Run: gemini mcp add --transport http --scope user resumebooster https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp
Ask: call board_stats.

With a key: gemini mcp add --transport http --scope user --header "Authorization: Bearer $RESUMEBOOSTER_KEY" resumebooster https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp. Or install this repository as an extension — it declares the key as a setting, prompted at install and kept in your keychain:

gemini extensions install https://github.com/campbellaabbott-rgb/resumebooster-mcp

When sign-in is on — /mcp auth resumebooster starts the sign-in.

How you know it worked: "call board_stats" answers with the count and the unkeyed note.

Codex CLI

Run: codex mcp add resumebooster --url https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp
Ask: call board_stats.

With a key, in ~/.codex/config.toml (the key is read from RESUMEBOOSTER_KEY, never written here):

toml

[mcp_servers.resumebooster]
url = "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
bearer_token_env_var = "RESUMEBOOSTER_KEY"

When sign-in is on — codex mcp login resumebooster starts the sign-in.

How you know it worked: "call board_stats" answers with the count and the unkeyed note.

Cline

In the Remote Servers tab: Server Name resumebooster, Server URL https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp, Transport Type Streamable HTTP, then Add Server. Or paste the block below into ~/.cline/mcp.json (the Cline CLI's file; in the VS Code extension, open the MCP Servers panel, the Configure tab, then Configure MCP Servers and add the same block).
Ask: call board_stats.

json

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

With a key: add "headers": { "Authorization": "Bearer …" } with your key to that server, in your own user-level file only — never in a committed one.

How you know it worked: "call board_stats" answers with the count and the unkeyed note.

Zed

Paste the block below into settings.json.
Zed prompts you to sign in whenever no Authorization header is set (its own document says so). If the curl above prints "off", that prompt cannot finish — add "headers": { "Authorization": "Bearer …" } with a free key from https://resumebooster.work/data-api to the block, in your own settings file only.
Ask: call board_stats.

json

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

How you know it worked: "call board_stats" answers with the count and the unkeyed note.

Windsurf

Paste the block below into ~/.codeium/windsurf/mcp_config.json. Windsurf's document says this file configures the legacy Cascade agent only; the Devin Local agent, the default for new tabs, reads the Devin CLI config files instead.
Ask: call board_stats.

json

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

With a free key, the same file names the variable and Windsurf fills it in (${env:RESUMEBOOSTER_KEY} is resolved in headers), so the key never sits in the file:

export RESUMEBOOSTER_KEY=<paste your key here>

json

{
  "mcpServers": {
    "resumebooster": {
      "serverUrl": "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp",
      "headers": {
        "Authorization": "Bearer ${env:RESUMEBOOSTER_KEY}"
      }
    }
  }
}

How you know it worked: "call board_stats" answers with the count and the unkeyed note.

Any client / curl

POST one JSON-RPC 2.0 message per request to https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp (Streamable HTTP; no session to keep); the first one is the initialize message below.
With a key, send Authorization: Bearer <key> on each request; without one, board_stats, search_jobs, search and fetch still answer.

curl -s -X POST https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp -H 'content-type: application/json' -H 'mcp-protocol-version: 2025-06-18' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"0"}}}'

How you know it worked: The initialize answer's serverInfo.name is resumebooster-job-board; the Test the server button on https://resumebooster.work/agents runs this for you.

Copy the prompt

For an agent that can install a server from prose, paste this: Add the MCP server "resumebooster" at https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp (Streamable HTTP, POST only, no key needed for board_stats, search_jobs, search, fetch; a free key from https://resumebooster.work/data-api goes in an Authorization: Bearer header). Then call board_stats.

How you know it worked: Your agent answers with the number of open postings and the unkeyed note.

If it does not work

Symptoms are the server's own words, or a label the app's documentation prints (docs-snapshot.md). Rows marked "while sign-in is off" or "on" apply in that state only — the curl line above prints today's.

What you see	Why	What to do
Sign-in through this server is not switched on yet, so this tool needs a key. (while sign-in is off)	The tool needs your account, and sign-in from chat apps is not switched on today.	Search, board statistics and full postings still work with no key. To use every tool, connect from Claude Code, Cursor or VS Code with a free key (https://resumebooster.work/data-api).
Claude: a Connect card appears (while sign-in is on)	A tool needs your account.	Click it, sign in to Resume Booster, press Allow; Claude retries the call itself.
Claude: "Couldn't reach the MCP server" or "Authorization with the MCP server failed"	The address was mistyped, `/mcp` was added to it, or (when sign-in is on) the sign-in could not finish.	Check the address is exactly `https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp`; press Test the server on https://resumebooster.work/agents; if the test says sign-in is on and the card still fails, remove the connector and add it again with Sign in when needed + Register automatically.
Claude Code: `/mcp` shows `! Needs authentication` (while sign-in is on)	A tool that needs your account was called with no key, and the server asked for sign-in.	Type `/mcp` and follow the browser steps (2.1.186 or newer: `claude mcp login resumebooster`), or add a free key with `--header`.
The unkeyed allowance is spent	Your network address used its 25 free calls today; an office or a chat service counts as one address.	Get a free key at https://resumebooster.work/data-api (1000 calls a day, no account) and add it to your app. Resets at midnight UTC.
That key is not recognised.	The key was cut off, or the header lacks `Bearer` with the space.	The header must read `Authorization: Bearer rb_live_…`. A key is shown once; get a new one if lost (the old one stops working).
This key has been revoked.	A newer key was made for the same account or email; only the newest works.	Use the newest key, or make one more and update every app that holds the old one.
Daily quota of	The free key's day is spent.	Wait for midnight UTC; the unkeyed tools still answer; an Agent Pass raises the limit for its hours.
requests/minute.	Too many calls in one minute.	Wait one minute.
fit_resume is a paid feature	Résumé fit scoring needs a paid key or a live Agent Pass.	https://resumebooster.work/data-api for a paid key, or https://resumebooster.work/agents/pass — search keeps working.
The apply agent needs an active Agent plan or a live pass.	Applying is paid.	https://resumebooster.work/agents/pass (sign in first), or the Agent plan on the site.
No agent mandate on this account.	The apply agent is not set up yet (the same answer names "Your agent is switched off." and "No resume on file" when that is the blocker).	Account → set up the apply agent: turn it on, choose countries and field, add the CV. The off switch always wins.
The pass on this account is not live.	The pass ended, or its applications are used ("No applications left on this pass.").	Search keeps working; buy another pass when the clock ends.
That is not a job id from this board.	You passed a link or a title.	Use the id from a search, e.g. `greenhouse:acme:12345`; the id in a `https://resumebooster.work/jobs?job=<id>` link is the same one.
This is an MCP server for AI agents, not a web page	You opened the address like a web page.	Nothing is wrong. Paste it into your agent; the how-to is https://resumebooster.work/agents.
Cursor / VS Code / Cline: server listed, zero tools	Wrong transport (Cline: not `sse`; VS Code: `"type": "http"`), or `/mcp` appended to the address.	The address ends in `/agent-mcp` exactly; the transport is HTTP (Cline: Streamable HTTP).
ChatGPT only ever searches and fetches	By design: ChatGPT's search calls `search` and `fetch`, 10 results a page.	For filters (pay, remote, seniority), use an app that calls `search_jobs`.
Sign in to use this tool (while sign-in is on)	A tool that needs a key was called with none (HTTP 401 from a script or curl).	Send `Authorization: Bearer <key>` (free at https://resumebooster.work/data-api), or call one of `board_stats`, `search_jobs`, `search` and `fetch`.

The plugin's skills

/resumebooster:setup — get a free key, put it in RESUMEBOOSTER_KEY, reconnect.
/resumebooster:find-jobs — the search → verify → apply order, with the gates named.

Privacy

Every search you run travels to the server as the query you typed. A key is stored as its hash and its first characters, never the key. For unkeyed calls the server keeps a truncated hash of your network address for the daily cap and drops it after 7 days; the address itself is never stored. The tools never write to your machine. A key belongs in an environment variable, a keychain prompt or a host's secret store — never in a file you commit, a URL, a badge or a base64 config. Nothing in this repository carries a key.

This repository

mcp.config.json is the only place a URL, tool name, cap, quota, host step or troubleshooting row is written. npm run build regenerates every other file; npm test fails if any generated file was edited by hand or the constants changed without a rebuild, validates each manifest against the schema its host publishes (copies under schemas/, fetched 2026-09-16), and checks that no generated file carries a placeholder inside an Authorization value.
The tool list, the host ids (the six above and the long tail) and the sign-in key are a mirror of the site's own (resume-signal-pro/src/config/mcp-tools.ts at 7266f38c); when that changes, this file is re-synced and rebuilt.
Every vendor label in the steps above is quoted from the vendor's documentation on the date in docs-snapshot.md; a label that is not there is not published here.
server.json is the entry for the official MCP Registry.

License

MIT — for the files in this repository. The server, the board and its data are https://resumebooster.work's own and are governed by its terms.

Install

Tools (15)

search_jobsget_jobget_jobscheck_jobs_opencheck_apply_supportrequest_applicationapplication_statusfit_resume

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

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

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "jobs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://bwhdazbotpblihdxcmho.supabase.co/functions/v1/agent-mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

work.resumebooster/jobs — Model Context Protocol (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

search_jobs

get_job

get_jobs

check_jobs_open

check_apply_support

request_application

application_status

fit_resume

board_stats

employer_hiring_record

employer_growth

key_status

debug_search

search

fetch

Resume Booster Job Board — MCP server

Tiers

Install

Claude (claude.ai, Claude Desktop, Claude on your phone)

ChatGPT (developer mode)

Claude Code

Cursor

VS Code

More… (Gemini CLI, Codex CLI, Cline, Zed, Windsurf, anything else)

Gemini CLI

Codex CLI

Cline

Zed

Windsurf

Any client / curl

Copy the prompt

If it does not work

The plugin's skills

Privacy

This repository

License

Install

Remote endpoint

Related servers