Skip to main content
Glama

Server Details

Your job search in one place: resumes, the jobs you track, daily matches, interviews, next step.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
resumequick/resumequick-mcp
GitHub Stars
0
Server Listing
ResumeQuick MCP Server
ChatGPT
–
Claude
ResumeQuick

TDQS

A3.8/5.0

Scored across 81 tools

Disambiguation3/5

Most tools target genuinely distinct resources, and descriptions go out of their way to cross-reference siblings (e.g. analyze_vacancy vs analyze_tracked_vacancy vs analyze_radar_match, create_reminder vs create_reminders, get_resume_pdf_url vs share_resume_link). However, with 81 tools there are several clusters an agent can easily misselect from: the four analyze_* variants, the resume-suggestion quartet (get_resume_suggestions / request_vacancy_resume_suggestions / apply_vacancy_resume_suggestions / set_vacancy_suggestion_declined), and the archive_/delete_ trios. The boundaries are documented but not self-evident from the names.

Naming Consistency4/5

Names are overwhelmingly snake_case verb_noun (list_resumes, archive_vacancy, set_radar_filters, cancel_reminder), which makes scanning predictable. Minor deviations exist: score_resume/read_job_link/check_radar_place put the verb first but read oddly, export_resume_pdf is noun-heavy, and start_without_resume has no object noun. Nothing rises to mixed-convention chaos.

Tool Count1/5

81 tools is far past any reasonable agent-facing surface, even for a broad job-search product spanning resumes, radar, vacancies, offers, interviews, reminders, coaching, guilds and billing. Many tools are thin variants of each other, so the count reflects surface sprawl rather than distinct capability. This is an extreme mismatch.

Completeness4/5

Coverage is unusually deep: full resume lifecycle (create, version, restore, style, PDF, share link), vacancy analysis/tracking, radar lifecycle, offers, reminders, career memory, coach plan and usage/pricing. Notable gaps remain: mock interviews can only be listed, archived and deleted — there is no tool to start or answer one — and offers cannot be archived or deleted via tools. These are real but workable omissions in an otherwise complete surface.

Available Tools

81 tools
add_career_factRemember a career factAInspect

Remember a single durable career fact about the user (e.g. 'Led a 5-person backend team', 'Wants to move into management'). Append-only. Vacancy analysis reads the 15 newest facts for where the user lives or can work, the work model they accept and their work authorization; the same preferences as structured fields are locations, remote_preference and work_authorization in upsert_career_memory. Returns the new fact_id. Returns 'invalid_payload' if the fact is empty or over 500 characters.

Inputs: input (required). Returns: text, fact_id

analyze_offerAnalyze a job offerAInspect

Analyse a job offer the user received and draft the negotiation scripts. Takes the offer text exactly as they got it — the recruiter's email, message or their own notes; the numbers are extracted from that wording, so a retold or summarised version loses them. Runs asynchronously: this returns an offer_id immediately, and get_offer(offer_id) shows the verdict, the market comparison and the counter-offer email once done. vacancy_id links the offer to a tracked vacancy. The market is read for where the user lives and how they are hired: pass candidate_country, employer_country and employment_type when the user said them; a left-out country is taken from their profile. Counts as one offer analysis against the user's plan — the free plan allows one a month. Returns 'limit_exceeded' naming the day it frees up when the quota is spent, 'no_resume' when the user has no resume to compare against, 'draft_limit_reached' when too many offers are waiting to be finished, 'not_found' for a foreign vacancy_id, and 'invalid_payload' for empty or oversized text.

Inputs: input (required). Returns: status, task_id, offer_id

analyze_radar_matchAnalyze a job matchAInspect

Analyze one radar match (by match id) against the user's resume, using the posting text the radar already stored; it does not fetch the job page. Some boards hand over only a teaser (under 400 characters): such a match is not analyzed and spends nothing; it is put in the tracker unanalyzed and comes back with status='needs_full_posting'; analyze_tracked_vacancy with the full posting text as 'description' analyzes it. Otherwise consumes one vacancy analysis from the user's quota per match. Runs asynchronously: get_vacancy_detail(analysis_id) shows the result in a few seconds. If this match was already analyzed the existing analysis is returned with reused=true and nothing is spent. Returns 'limit_exceeded' naming the day it frees up when the quota is gone, 'posting_closed' when the job board says the posting is gone (closed_at is set; the match is put away and nothing is spent), 'no_resume' when the account has no resume yet (nothing is spent), and 'not_found' if the match does not belong to the current user.

Inputs: input (required). Returns: reused, status, task_id, match_id, +1 more

analyze_tracked_vacancyAnalyze a tracked jobAInspect

Analyze a vacancy already in the user's tracker (by vacancy_id) against their active resume, in place — no duplicate is created. It covers a vacancy never analyzed (analysis_status 'none'), one whose analysis failed, and a re-run (e.g. the first read a truncated posting). Consumes one vacancy analysis from the user's quota; while the posting text, the resume and what the user told are as they were, the last analysis stands and nothing is spent (status 'completed', reused true). Runs asynchronously: get_vacancy_detail(vacancy_id) shows the result once done, usually within 10 seconds. Returns 'description_required' when the vacancy has no posting text (pass the user's pasted text as 'description'), 'posting_too_short' when a never-analyzed vacancy holds only a job board's teaser of under 400 characters (nothing analyzed or spent; the full posting text passed as 'description' lifts it), 'already_processing' when an analysis of it is already running (nothing spent), 'limit_exceeded' naming the day it frees up when the quota is gone, and 'not_found' if the vacancy does not belong to the current user.

Inputs: input (required). Returns: reused, status, task_id, analysis_id

analyze_vacancyAnalyze a job postingAInspect

Analyze the text of a job posting that is not in ResumeQuick yet against a resume. Creates a NEW vacancy in the tracker; a vacancy already in the tracker is analyzed in place by analyze_tracked_vacancy, a radar match by analyze_radar_match. The same posting text analyzed before returns that analysis with status 'completed' and spends nothing, unless the resume or what the user told about themselves changed since; force=true re-runs it. Runs asynchronously — this returns an analysis_id immediately; get_vacancy_detail(analysis_id) shows the match, verdict and gaps once done, usually within 10 seconds. company, location and url are stored on the vacancy, shown on the tracker card, and make the analysis findable by search_vacancies(location=...). Counts as one vacancy analysis against the user's plan; text that turns out not to be a job posting ends with verdict 'invalid' and spends nothing. Returns 'not_found' if resume_id is given but does not belong to the current user, 'no_resume' when the account has no resume yet (nothing is spent), and 'limit_exceeded' naming the day it frees up if the plan quota is reached.

Inputs: input (required). Returns: reused, status, task_id, analysis_id, +1 more

answer_vacancy_placeAnswer a vacancy's place questionA
Idempotent
Inspect

Record whether the person lives in or can relocate to the place a posting requires, on a vacancy with an 'unverified' eligibility blocker. Yes adds the place to career memory's locations, no is kept as the person's own words; the analyses after it judge the place. This vacancy keeps its verdict: on yes the blocker goes, on no it stays as a 'soft' one. No quota. Errors: not_found (vacancy not theirs), invalid_payload (the vacancy has no open place question).

Inputs: input (required). Returns: saved_as, vacancy_id

answer_vacancy_statusAnswer a vacancy's status questionA
Idempotent
Inspect

Record whether the person has the status a posting requires, on a vacancy whose verdict_category is 'confirm_status'. The answer goes into career memory and settles this vacancy: with the status the blocker goes and the verdict follows the match, without it the verdict is 'not_eligible'. match_percentage does not change. No quota. Errors: not_found (vacancy not theirs), invalid_payload (the vacancy has no open status question).

Inputs: input (required). Returns: vacancy_id, verdict_category

apply_vacancy_resume_suggestionsApply resume suggestions for a jobAInspect

Apply resume-improvement suggestions from a vacancy analysis. indices (into the vacancy's resume_suggestions list from get_vacancy_detail) pick which to apply; omitted applies all except the questions without a fact and the suggestions whose last apply changed nothing (unchanged_suggestion_indices). target='copy' rewrites an inactive tailored copy linked to this vacancy (reused when it exists, otherwise duplicated from the active resume — consumes one resume generation, 'limit_exceeded' on quota, naming the day it frees up); target='current' rewrites the active resume. Without target it goes where the Tailoring tab defaults: the copy when one exists or a resume generation is left, otherwise the active resume; copy_created and resume_id in the output say which. Runs asynchronously — returns a task_id and the target resume_id; each applied suggestion saves a new resume version; get_task_status(task_id) reports progress and the outcome, with unchanged_count for suggestions that changed nothing because the resume states nothing they build on. A suggestion whose kind is 'needs_fact' is a question to the user: it applies only with their own answer in facts. Returns 'not_found' if the vacancy does not belong to the current user, 'invalid_payload' if there are no suggestions, an index is out of range, a fact is too long or nothing is left to apply, 'fact_required' if a 'needs_fact' index has no fact.

Inputs: input (required). Returns: status, task_id, resume_id, vacancy_id, +1 more

archive_interviewArchive or restore a mock interviewA
Idempotent
Inspect

Archive a mock interview (hide it from the user's main list) or restore it. This is the 'remove it from my list' action: reversible, the results are kept, and the archive never expires. archived=false restores. Returns 'not_found' if the interview does not exist or does not belong to the current user.

Inputs: input (required). Returns: id, is_archived

archive_radar_matchArchive or restore a job matchA
Idempotent
Inspect

Put a saved radar match away in the radar archive, or restore it to the saved pile with archived=false. Reversible, applies instantly, no quota. The archive keeps matches until the user deletes them; read it with get_radar_matches(status="archived"). Returns 'not_found' if the match does not belong to the current user.

Inputs: input (required). Returns: id, status

archive_vacancyArchive or restore a tracked jobA
Idempotent
Inspect

Archive a tracked vacancy (hide it from the user's main list) or restore it. This is the 'remove it from my list' action: reversible, history and quota accounting stay intact, and the archive never expires. archived=false restores. Returns 'not_found' if the vacancy does not exist or does not belong to the current user.

Inputs: input (required). Returns: id, is_archived

cancel_all_remindersCancel all remindersA
Idempotent
Inspect

Cancel every active reminder of the user at once and return how many went (0 when there were none). Nothing brings a cancelled reminder back, so this belongs behind an explicit request. Applies instantly, no quota.

Inputs: no named parameters. Returns: cancelled

cancel_reminderCancel a reminderA
Idempotent
Inspect

Cancel one of the user's active reminders by id (see list_reminders). Applies instantly, no quota. Returns 'not_found' when the reminder does not belong to the current user, has already fired, or does not exist.

Inputs: input (required). Returns: id, cancelled

check_radar_placeCheck a radar placeA
Read-only
Inspect

Whether set_radar_filters would accept these cities. Saves nothing. Refuses with the same 'invalid_payload' errors: ambiguous_city, city_not_supported, unknown_city, city_country_mismatch.

Inputs: input (required). Returns: searchable

create_profileCreate the first resume profileAInspect

Create the first resume of an account that has no profile yet, either from the text of the user's resume (resume_text) or from five answers about their work (guided: role, years of experience, education, skills, last job). Given both, resume_text is used and guided is ignored. It works before setup is finished and completes setup once the resume is saved. Runs asynchronously — returns a task_id immediately; get_task_status(task_id) reports progress and, when done, the new resume_id. Consumes one resume generation from the user's plan; on the free plan this is the month's only resume generation. Once the resume is saved, the job radar's automatic search is turned on and its first scan runs, built from the resume and the account's country; the account's first scan is not counted against the radar quota. get_radar_status shows the search, and set_radar_auto_search turns it off. The profile's name is the account's name. Guided answers without last_job leave the experience section empty. language defaults to the account's language and is one of: en_EN, ru_RU, es_ES, pt_BR, de_DE, fr_FR, it_IT, tr_TR, hi_IN, uk_UA, id_ID, ja_JP. Returns 'already_set_up' if the account already has a profile, 'limit_exceeded' naming the day it frees up if the plan quota is reached, and 'invalid_payload' when neither input is given or the language code is unknown.

Inputs: input (required). Returns: status, task_id

create_reminderCreate a reminderAInspect

Schedule a reminder for the user. fire_at_local is their local wall clock time as ISO 8601 with no zone; the server converts it. text is delivered as written, on its own, when the reminder fires. Applies instantly, no quota. Returns 'limit_exceeded' at 20 active reminders and 'invalid_payload' for a time in the past, more than 180 days ahead, or empty text.

Inputs: input (required). Returns: id, text, fire_at_local

create_remindersCreate several remindersAInspect

Schedule several reminders at once — one thing spread over several dates, up to 20 per call. Each entry takes fire_at_local (the user's wall clock, ISO 8601, no zone) and text, delivered as written when it fires. All or nothing: 'limit_exceeded' says how many of the user's 20 reminder slots are free, so ask for at most that many or free some with cancel_reminder; 'invalid_payload' names the entry (reminders[i]) whose time is past, more than 180 days ahead, or whose text is empty. Applies instantly, no quota.

Inputs: input (required). Returns: reminders, free_slots

create_resume_versionCopy a resumeAInspect

Create a new draft resume as a copy of an existing one — the original is left untouched. Optionally pass a vacancy_id to tailor against; it names the draft and links the copy to that vacancy (shown on the vacancy card and as a badge in the resume manager). Counts as one resume generation against the user's plan. Returns 'not_found' if the source resume (or vacancy) does not exist or does not belong to the current user, and 'limit_exceeded' naming the day it frees up if the plan quota is reached.

Inputs: input (required). Returns: id, name, vacancy_id, content_version, +1 more

delete_interviewDelete an archived mock interviewA
Destructive
Inspect

Permanently delete an ARCHIVED mock interview — its questions, answers, feedback and public share link are gone. Irreversible. A retry of it survives with its link cleared (the response counts them). Returns 'not_archived' if the interview is still active: archive it first with archive_interview, which is what the user usually means by 'remove it'. Find archived ids with get_interview_results(archived=true). Returns 'not_found' if it does not exist or does not belong to the current user. Consumes no quota and refunds none.

Inputs: input (required). Returns: id, deleted, retries_unlinked, reminders_cancelled

delete_radar_matchDelete a skipped job matchA
Destructive
Inspect

Permanently delete a radar match from the Skipped pile — status skipped or archived, as get_radar_matches(status="archived") lists them. Irreversible, no quota. The vacancy will not come back in future radar scans; a vacancy analysis made from this match is NOT deleted and stays in the job analysis list. Returns 'not_archived' if the match is new, saved or deferred, and 'not_found' if it does not belong to the current user. Clearing the whole radar archive at once is deliberately web-only.

Inputs: input (required). Returns: id, deleted

delete_resumeDelete a resumeA
Destructive
Inspect

Permanently delete a resume; its PDF files are deleted too, and links to them stop working. Irreversible; the resume generation spent on it is not returned. Returns 'not_found' if the resume does not exist or does not belong to the current user, 'cannot_delete_active' if it is the currently active resume, and 'cannot_delete_only' if it is the user's only resume.

Inputs: input (required). Returns: id, deleted

delete_vacancyDelete an archived jobA
Destructive
Inspect

Delete an ARCHIVED vacancy. The vacancy and its history leave the user's lists at once and are erased for good a day later; until then the web app's Undo brings it back, and no tool here does. The tailored resume made for it goes with it when that copy is not the active resume and the vacancy is still at status new; otherwise a linked tailored resume, interview or offer survives with its link cleared, and the radar match it came from is deleted too and not offered again (the response counts them). Returns 'not_archived' if the vacancy is still active: archive it first with archive_vacancy, which is what the user usually means by 'remove it'. Returns 'not_found' if it does not exist or does not belong to the current user. Consumes no quota and refunds none.

Inputs: input (required). Returns: id, deleted, offers_unlinked, interviews_unlinked, +4 more

export_resume_pdfExport resume as PDFAInspect

Generate the PDF of a resume — the exact file the user downloads, never watermarked. An unchanged resume is handed back without a new render: the reply then has status 'completed' and the file itself (file_name, pages, and pdf_url that saves it for 60 minutes). Otherwise it renders asynchronously: a task_id comes back at once, the PDF is usually ready in a few seconds, get_task_status(task_id) reports progress and the outcome, and get_resume_pdf_url then gives the file. No quota on any plan. Returns 'not_found' if the resume does not exist or does not belong to the current user.

Inputs: input (required). Returns: reused, status, made_at, pdf_url, +7 more

forget_career_factForget a career factA
Destructive
Inspect

Forget a single career fact by its id (as returned by get_career_memory). A forgotten fact no longer reaches vacancy analysis or the agent. Returns 'not_found' if the fact does not exist, was already forgotten, or does not belong to the current user.

Inputs: input (required). Returns: deleted, fact_id

generate_cover_letterWrite a cover letter for a jobAInspect

Write the cover letter for a vacancy in the user's tracker, from their resume and the analysis, with an optional tone, length, up to three of the vacancy's key_strengths to lead with, and a personal note. The letter is written in the user's profile language and states only facts from the resume; a resume with no work history still gets a letter, built from its summary and skills. The letter is saved on the vacancy's Cover Letter tab in the web app, the same letter the web and the browser extension write. When the vacancy already has a letter, this replaces it: the new one is written with the previous version in view and the change in options, and an option not given keeps the value the previous letter used. Runs asynchronously — returns a task_id; get_task_status reports when it is written, and get_vacancy_detail then shows has_cover_letter: true. The letter text itself is not returned. Spends one cover letter from the plan (the free plan has one a month); replacing an existing letter spends another one. Returns 'not_found' if the vacancy does not belong to the current user, 'no_resume' if the user has no resume, 'limit_exceeded' naming the day it frees up if the plan allowance is used up.

Inputs: input (required). Returns: status, task_id, vacancy_id

get_career_memoryRead career memoryA
Read-only
Inspect

Get what is remembered about the user's career — target roles, locations, remote preference, seniority goal, industries, salary expectation, work authorization, search stage, blockers, motivation, plus free-form facts (each with an id you can pass to forget_career_fact). Empty if nothing is stored yet. Args: {}.

Inputs: no named parameters. Returns: facts, blockers, locations, industries, +7 more

get_career_tipsSearch career tipsA
Read-only
Inspect

Get short, fact-checked career cards to ground advice in — recruiter behaviour, ATS, resumes, cover letters, interviews, salary, networking. Filter by set_id, by free-text query, or to only_owned (cards the user has already collected). A query is matched word by word: a card qualifies when its title or body holds at least half of the query's words (words under 3 letters are ignored), cards matching more words first. Args: {set_id?, query?, only_owned?, limit? (default 10, max 30)}.

Inputs: input (required). Returns: sets, tips

get_coach_planRead the weekly planA
Read-only
Inspect

Get the weekly job-search plan the user agreed — goal, target roles, applications a week, review day, active or paused — and this week's progress in the user's timezone: applications marked sent (with the vacancies behind the number), analyses, vacancies that got a cover letter, mock interviews and employer replies. Progress counts only what was done. plan is null when no plan was agreed. Args: {}.

Inputs: no named parameters. Returns: plan, week

get_collectionRead collected career cardsA
Read-only
Inspect

Get the career cards this user has collected: what, when it was earned and how (deck | loader | agent | milestone | import). Milestones record work the user actually did — a first analysis, an offer, an interview scored 80+. There is no total to collect and no progress counter: the list holds only what has been earned. Args: {}.

Inputs: no named parameters. Returns: items, counts

get_guild_newsRead the guild newsA
Read-only
Inspect

Get what is new for the user in the guilds — six guilds by what people love in their work, a shared feed of job-search steps with cheers — and the games about the world of work: their nickname and guild, how many people cheered their one latest cheered step or day of steps in the last 7 days, and whether they finished today's Two truths and a lie, today's Closest guess and this week's Connections. Never other people's identities, member counts or rankings. available is false when the guilds are not open to the user. Args: {}.

Inputs: no named parameters. Returns: path, games, cheers, member, +1 more

get_interview_resultsList mock interview resultsA
Read-only
Inspect

List the user's completed mock interviews, newest first. Each item includes overall score, role, key feedback aggregated from the lowest-scoring questions, and weak study topics. Default limit 5, max 20. Archived interviews are excluded; pass archived=true to list the archive instead. Empty list is a normal result.

Inputs: input. Returns: interviews

get_market_snapshotJob market snapshot from the radarA
Read-only
Inspect

What the job postings ResumeQuick's radars found in the last four weeks say about a role, in one country or everywhere: how many distinct postings, last week against the week before, the remote share, salary quartiles as the postings stated them, the skills they name most and three fresh links. It covers what the radars found, not the whole market. Under 30 postings enough_data is false and only the count is given. Errors: invalid_payload (no role words, unknown country).

Inputs: input (required). Returns: role, weeks, salary, country, +7 more

get_next_stepGet the next stepA
Read-only
Inspect

Get the user's one next step in the job search — the same step the ResumeQuick home screen shows — with the reason from their data and, when the step is about a vacancy, that vacancy and the step inside it (vacancy.vacancy_step), and app_url — the screen in ResumeQuick where the step is done. After an application the vacancy leaves the ladder and has no step until the employer answers; the ladder has no follow-up step for it, and the step moves to new radar matches or another analysed vacancy. Args: {}.

Inputs: no named parameters. Returns: step, match, radar, reason, +3 more

get_offerRead an offer analysisA
Read-only
Inspect

Full analysis of one offer: health score 0-10, verdict (negotiate / accept / decline) with its reasoning, each pay component against an estimated market range, red and green flags, leverage points with a current -> ask delta and the chance each lands, and four ready-to-send scripts (counter-offer email, reply when the budget is fixed, call talking points, polite decline). Status is 'processing' while the analysis runs and 'completed' once it is done. Market ranges are estimates, not the company's pay bands: each line carries a confidence (a low one claims no position), and market_assumptions names the country and hire type they were read for — say that once with the result. Returns 'not_found' for a missing or foreign offer id.

Inputs: input (required). Returns: id, role, tone, bonus, +37 more

get_pricingRead plans and pricesA
Read-only
Inspect

Get the current pricing catalog — subscription tiers and action packs with their USD prices, how many days one payment buys and whether it renews, the per-plan limits for free / sprint / career, and the user's current tier. Prices are the same for all users. This is the live source of ResumeQuick prices and limits.

Inputs: no named parameters. Returns: skus, plans, currency, current_plan

get_profile_snapshotRead profile summaryA
Read-only
Inspect

Get a compact summary of the current user's primary resume — name, headline, location, top skills, last 2 experiences, and languages. Returns 'not_found' if the user has no resumes; an account that has not finished setting up its profile gets an empty summary with that fact instead.

Inputs: no named parameters. Returns: name, summary, headline, location, +3 more

get_quick_workRead what Quick didA
Read-only
Inspect

What Quick did on its own on the user's jobs: each find it worked on, newest first — the weekly find it prepares at no cost to the user (origin gift), and, when Quick works from the plan's limits (origin engine), the analysis, resume suggestions, a tailored resume copy, a cover letter or an archive of a job the profile rules out. Every step carries its result and the reason as a code. Also says whether Quick is working on its own (enabled) and whether the plan allows it (included: Sprint and Career). No quota. Args: {limit, before}.

Inputs: input. Returns: items, enabled, included, next_before

get_radar_matchesList job matchesA
Read-only
Inspect

List vacancies the user's job radar has found (automatic job search based on their resume), best match first. Each item carries title, company, location, match_grade (strong/possible/weak — the radar's rough fit; match_percentage is the same guess as a number and does not predict an analysis; both are null once the match is analyzed), the keywords behind it, the published salary when the board gave one, the applicant-tracking system behind the link, the level and employment type its title states (null when it states none), an opening snippet of the posting text and on_screen (whether the user has seen it in the app yet), analysis_id when this vacancy was already analyzed, with analysis_match_percentage once that analysis finished — then the only fit to quote (get_vacancy_detail reads it at no cost; analyze_radar_match analyzes one that has none). The stored snippet is all the posting text we hold. Optional status: 'new' (not yet reviewed) or 'saved' (liked) pick one half of the active list; 'deferred' reads the put-off-for-later pile and 'archived' the Skipped pile — everything the user skipped or put away, latest first, and where delete_radar_match takes its ids from. Omit for new plus saved. Narrow with min_match, is_remote, source, posted_after (ISO date), has_analysis, seniority and employment_type — the last two come from the title, so a posting whose title says nothing is dropped by them: a small result means most titles were silent, not that such jobs are rare. Order with sort='fresh' (newest posting first) instead of the default best-match. total says how many matched the filters; offset pages past the 30-item cap. Empty list is a normal result, and the usual one before the first start_radar_scan.

Inputs: input. Returns: total, matches

get_radar_statusRead job search statusA
Read-only
Inspect

State of the user's job radar: how many matches are in the working list, still waiting in the pool, saved, deferred or in the Skipped pile ('archived' counts what was skipped and what was put away); when a scan last brought something in; whether the daily automatic search is switched on; and the explicit search filters, if the user set any — the progress picture without paging through every match. last_scan_at moves when new vacancies arrive, so a scan that found nothing new leaves it unchanged. search_query is what the last scan actually searched for (role, place, country) — the role there came from the filters, career memory or the resume, so an empty filters.role does not mean the radar searched for no role; search_query.role is the title the boards were searched with and search_query.role_display the same role in the user's own words, as typed in the filters; search_role is what the next scan searches for (null: nothing names a role yet). next_scan_at is set only on the free plan while its one scan a week is spent. All zeros with auto_search_enabled=false is the normal answer for someone who has never used the radar.

Inputs: no named parameters. Returns: saved, active, filters, archived, +8 more

get_recent_activityRead recent activityA
Read-only
Inspect

List the user's recent profile-affecting events — resumes created or updated, vacancies analyzed (archived analyses included), mock interviews completed — within the last days (default 30, max 180), newest first, at most limit of them (default 20, max 50). Empty list is a normal result.

Inputs: input. Returns: range, events

get_recent_vacanciesList tracked jobsA
Read-only
Inspect

List the user's tracked vacancies, pinned first (is_pinned), then newest by analyzed_at: finished fit analyses (match percentage, verdict, key strengths and gaps) and vacancies tracked without an analysis (analysis_status 'none', match fields null). Vacancies with an analysis still running or failed are not listed. Filters: tracker status, analysis_status. total says how many match in all. Default limit 10, max 50. Empty list is a normal result.

Inputs: input. Returns: total, vacancies

get_resumeRead a resumeA
Read-only
Inspect

Get a specific resume by id, including all 12 editable sections (full_name, title, contacts, summary, experience, education, skills, projects, languages, interests, publications, references) plus the current visual style. Sections use the exact shapes and field names update_resume_section accepts, and every list entry carries an 'id' to echo back in edits. Returns 'not_found' if the resume does not exist or does not belong to the current user.

Inputs: input (required). Returns: id, undo, style, title, +15 more

get_resume_historyList resume versionsA
Read-only
Inspect

List the saved versions of a resume, newest first; each version is the resume content as saved at that moment. Per version: when it was saved, what produced it (the user's editor, an agent edit, an AI rewrite, an import, a restore…), entry counts per section and which sections changed against the version before, so the version where missing content was last present can be found by its counts. Returns 'not_found' if the resume does not exist or does not belong to the current user.

Inputs: input (required). Returns: resume_id, revisions

get_resume_pdf_urlGet resume PDF linkA
Read-only
Inspect

Get the latest downloaded PDF of a resume — what the user actually gets when they download it: its file name, pages, when it was made, and an address on ResumeQuick.app that saves it for 60 minutes (expires_at). The address is the user's own copy and creates no public link; share_resume_link makes the link for other people. Returns 'not_generated' when no download has been made yet (export_resume_pdf makes one in a few seconds), and 'not_found' if the resume does not exist or does not belong to the current user. is_current says whether the file still matches the resume as it is now.

Inputs: input (required). Returns: made_at, pdf_url, file_name, resume_id, +3 more

get_resume_revisionRead a resume versionA
Read-only
Inspect

Get one saved version of a resume (revision_id from get_resume_history) with all 12 sections in the shape get_resume returns. Entry ids here belong to that old version: to bring one entry back, send it to update_resume_section as a new entry without its id; to bring the whole version back, use restore_resume_revision. Returns 'not_found' if the resume or the version does not exist or does not belong to the current user.

Inputs: input (required). Returns: id, undo, style, title, +16 more

get_resume_suggestionsRead resume improvement suggestionsA
Read-only
Inspect

Get a prioritized list of concrete improvements for a resume by id, each tagged with the section it applies to (formatting, content, completeness, length) and a priority. Highest-impact issues first. The suggestion text is in English, whatever the resume's language. score_resume gives the numeric assessment. No quota — the resume_suggestions action in get_usage belongs to request_vacancy_resume_suggestions. Returns 'not_found' if the resume does not exist or does not belong to the current user.

Inputs: input (required). Returns: resume_id, suggestions

get_task_statusCheck a background taskA
Read-only
Inspect

Report a background task by the task_id a tool returned (create_profile, translate_resume, request_resume_update, export_resume_pdf, start_radar_scan, apply_vacancy_resume_suggestions, generate_cover_letter and the analyze_* tools): status processing | completed | failed | cancelled, progress, on failure the reason, and on success what it produced — the new resume's resume_id, the translated copy's resume_id, the resume_id a rewrite changed (get_resume reads it) and the sections it kept as they were (guarded_sections), whether the PDF is ready, how many postings a scan found, the app_url of a written cover letter. Returns 'not_found' if the task does not exist or does not belong to the current user.

Inputs: input (required). Returns: type, error, result, status, +4 more

get_usageRead my usage and limitsA
Read-only
Inspect

Get the user's own use of their plan: for each limited action, how many uses the current period counted, the allowance, and how many are available now; when a calendar period (day, month) resets, and for rolling windows (week, 30 days) when the oldest use drops out; bonus and pack credits, which buy uses beyond an allowance; and when a paid plan or trial ends. A resume generated in the background from text or answers (create_profile, the web onboarding) counts against resume_generation. Radar scans are not bought with bonus or pack credits. Bonus and pack credits are one shared pool: it is part of remaining for every action, so a credit spent on one action lowers remaining for all of them. A null limit or remaining means no limit. Reading job links (read_job_link) is not listed here; its own limit is in read_job_link. The actions listed are the same ones get_pricing gives limits for. Plan prices and the limits of other plans are in get_pricing.

Inputs: no named parameters. Returns: plan, items, credits, plan_ends_at

get_user_statsRead job search statsA
Read-only
Inspect

Get a compact numeric summary of the user's activity over the last period_days (default 30, max 180): applications_count (vacancies the user marked as sent in the tracker), analyses_count (vacancies analyzed, archived analyses included) and avg_match_score, interviews_count and avg_interview_score, plus resumes_count (the user's total resumes, not windowed). Zero counts and zero averages are a normal result for a new user.

Inputs: input. Returns: period_days, resumes_count, analyses_count, avg_match_score, +3 more

get_vacancy_detailRead a job analysisA
Read-only
Inspect

Get one vacancy fit analysis by id, with match percentage, verdict, key strengths, gaps, recommendations, and a skill-by-skill requirements comparison, vacancy_step — the next step on this vacancy, and app_url — the vacancy's page in ResumeQuick. Returns 'not_found' if the analysis does not exist or does not belong to the current user.

Inputs: input (required). Returns: id, url, notes, title, +31 more

list_offersList job offersA
Read-only
Inspect

List the job offers the user has had analysed, newest first: company, role, base salary, offer health 0-10 and the verdict (negotiate / accept / decline). An offer still being worked on shows status 'processing' with a null score. archived: true reads the archive instead. get_offer(offer_id) holds the full verdict, the market comparison and the negotiation scripts.

Inputs: input (required). Returns: offers

list_remindersList remindersA
Read-only
Inspect

List the user's active reminders, soonest first. Times are on the user's local wall clock. Each carries the id cancel_reminder takes.

Inputs: no named parameters. Returns: reminders

list_resumesList resumesA
Read-only
Inspect

List all resumes belonging to the current user. Returns id, title (the document name, same as resume_name), last-updated timestamp and whether it is the active resume — the ids get_resume takes. Empty list is a normal result.

Inputs: no named parameters. Returns: resumes

pause_coach_planPause the weekly planA
Idempotent
Inspect

Put the user's weekly plan on hold: it is kept as it is and marked paused until set_coach_plan resumes it. No quota. Errors: not_found when no plan was agreed. Args: {}.

Inputs: no named parameters. Returns: plan, week

rename_resumeRename a resumeA
Idempotent
Inspect

Rename a resume DOCUMENT — the display name shown in the resume list. Not the job headline inside the resume content (that is update_resume_section with section 'title'). Returns 'not_found' if the resume does not exist or does not belong to the current user, and 'invalid_payload' if the name is empty.

Inputs: input (required). Returns: id, name

request_resume_updateRewrite a resumeA
Destructive
Inspect

Rewrite a resume from a natural-language instruction using the tuned LLM resume pipeline (ATS-aware, keeps the resume's own language). Runs asynchronously — returns a task_id immediately; the rewrite typically takes a few minutes, and a completion (or failure) message is posted into the user's chat when it finishes; get_task_status(task_id) reports progress and the outcome. It is for substantive rewrites ('rewrite my summary for a senior role', 'tighten all bullets', 'shorten the resume'); small structural edits are update_resume_section. NOT supported: translating the whole resume (that is translate_resume) and adding a photo (only the resume editor uploads one) — such requests fail. Consumes one resume update from the user's plan. source_text carries the user's own resume or full account of their experience, verbatim: the resume is then rebuilt from that text instead of being edited from the instruction. Returns 'not_found' if the resume does not belong to the current user, 'limit_exceeded' naming the day it frees up if the plan quota is reached, and 'invalid_payload' if source_text is longer than 20000 characters.

Inputs: input (required). Returns: status, task_id, resume_id

request_vacancy_resume_suggestionsSuggest resume changes for a jobAInspect

Generate structured resume-improvement suggestions tailored to a vacancy analysis. Runs asynchronously — this returns a task_id immediately; poll get_vacancy_detail(vacancy_id) and read 'resume_suggestions' for the completed list. The suggestions also appear in the web UI's vacancy analysis page. Counts as one resume-suggestions action against the user's plan. At a match of 90% or more no suggestions are generated and nothing is spent; the finished task then says skipped: 'high_match' in get_task_status. Returns 'not_found' if the vacancy does not belong to the current user, 'limit_exceeded' naming the day it frees up if the plan quota is reached.

Inputs: input (required). Returns: status, task_id, vacancy_id

restore_resume_revisionRestore a resume versionA
Destructive
Inspect

Bring an earlier saved version of a resume back as its current content (revision_id from get_resume_history) — for content that went missing or an earlier version the user wants back. Restoring is itself undoable: the current content is kept as a version first, and the result's new_revision_id can be restored in turn. Style and PDF are not touched. No quota. Returns 'not_found' if the resume or the version does not exist or does not belong to the current user.

Inputs: input (required). Returns: changed, resume_id, new_revision_id, undo_revision_id, +1 more

save_radar_matchSave a job matchA
Idempotent
Inspect

Save a radar match the user likes: keeps it in their list and teaches the radar to rank similar vacancies higher. Instant, free, no quota, no limit on how many. It does NOT analyze the vacancy: that is analyze_radar_match, which spends one vacancy analysis. Returns 'not_found' if the match does not belong to the current user.

Inputs: input (required). Returns: A save is only a save. It used to also start the tailored analysis and spend a…

score_resumeScore a resumeA
Read-only
Inspect

Score a resume's ATS quality (0-100) by id, with a per-area breakdown (formatting, content, completeness, length), a verdict and the checks that failed, each with its tip. Matches the resume editor's ATS badge — no AI guesswork. Use get_resume_suggestions for the actionable fix list. Returns 'not_found' if the resume does not exist or does not belong to the current user.

Inputs: input (required). Returns: verdict, resume_id, area_scores, checks_total, +4 more

search_vacanciesSearch tracked jobsA
Read-only
Inspect

Search the user's tracked vacancies: finished fit analyses and vacancies tracked without an analysis (analysis_status 'none'); ones with an analysis running or failed are not listed. Filter by free-text query (title, company, location, notes, description), minimum match percentage (drops unanalyzed ones), location (best-effort substring, falling back to the job description), tracker status and analysis_status. Newest first; total says how many match in all. Default limit 10, max 50. Empty list is a normal result.

Inputs: input. Returns: total, vacancies

set_active_resumeSet the active resumeA
Idempotent
Inspect

Make a resume the user's active one, deactivating all others. Returns 'not_found' if the resume does not exist or does not belong to the current user.

Inputs: input (required). Returns: id, is_active

set_coach_planSet the weekly planA
Idempotent
Inspect

Save the weekly job-search plan the user chose: goal in their words, target roles, applications a week, the day for the weekly review. Creates the plan or overwrites only the fields provided (omitted fields are kept; "" or [] clears one) and makes a paused plan active again. No quota. Returns the plan with this week's progress. Errors: invalid_payload: : .

Inputs: input (required). Returns: plan, week

set_quick_autoworkTurn Quick on or offA
Idempotent
Inspect

Turn Quick working on its own on (enabled=true) or off (enabled=false). On: at once, and again on each new save, Quick analyses the user's saved jobs and strong radar matches, prepares resume suggestions, tailors a resume copy when the job is worth it and writes a cover letter, spending the plan's own limits and keeping part of them for the user; it never applies. Off: it stops taking new jobs; ready work stays, and the weekly find Quick prepares at no cost comes back. Sprint and Career only: on the free plan turning on answers payment_required. Same switch as the Quick page in settings. Args: {enabled}.

Inputs: input (required). Returns: enabled, included

set_radar_filtersSet job search filtersA
Destructive
Inspect

Set what the user's job radar searches for — the search zone: role, locations (up to five cities of one country), country, radius_km around each city, work_modes (any of office, hybrid, remote) and employment_types (any of full_time, part_time, contract, internship — read off job titles, so a title that does not say it is kept), and resume_id — the resume jobs are matched against (omitted = the active one). An omitted city, country or list means any. These outrank the resume and apply to the daily automatic scan too, so this — not the scan tool — is how a search gets narrowed. It REPLACES the whole set: an omitted field is cleared, so the call carries the filters being kept along with the ones being changed. Changing the filters also hides matches found for the old search that they never saw — results ranked for a different query would otherwise crowd out the new ones for days. Hidden matches come back when the filters return to that search — including ones a scan under other filters found again in between — or a later scan finds the same posting again; saved and already-seen matches stay, and last_scan_at does not move. The place is one of: nothing (any country), a country, or a country and up to five of its cities, one radius around each (a job near any of them is in the zone). Any country may leave out up to five countries (excluded_countries): jobs placed only in them, or whose text takes applicants only from them ('Remote, United States only'), are never served — how 'not from India' is kept; with a country or city set this fails with 'invalid_payload: excluded_countries_need_any_country'. A country with no cities may leave out up to five of its cities (excluded_locations): office and hybrid jobs within 25 km of them are not served, remote ones are; with cities or no country this fails with 'invalid_payload: excluded_cities_need_country_only', and a city outside that country with city_country_mismatch. location alone still means one city. country_code is optional: with cities alone the server fills in the country when the name settles it, refuses when it does not, and stores the city as the settings list spells it. Only cities in that list are searchable. City errors: 'invalid_payload: ambiguous_city' — the name exists in several countries; 'city_not_supported' — not searchable, the error names the nearest listed city; 'unknown_city' — no such city in the list; 'city_country_mismatch' — the city is not in that country. Remote is a work mode, never a location. The role is typed, or omitted to search the resume's own (title, else latest position — never skills or remembered roles); the result's search_role says which, and null means nothing names one. Returns the radar's state, filters included. No quota.

Inputs: input (required). Returns: saved, active, filters, archived, +8 more

set_resume_styleSet resume styleA
Idempotent
Inspect

Change a resume's visual style: accent colour, layout, and/or font. Fields left out are preserved. accent_color: navy, emerald, burgundy, charcoal, violet (there is no pure red or blue). layout: classic, sidebar, header_banner, editorial, timeline, compact. font: default (Inter, sans-serif), classic (Lora, serif), modern (Jost, sans-serif). Applies instantly and returns the resulting style. Style is not part of resume versions: history and restore leave it as is. Returns 'not_found' if the resume does not exist or does not belong to the current user, and 'invalid_payload' if no field is provided or a value is not one of the allowed options.

Inputs: input (required). Returns: font, layout, resume_id, accent_color

set_search_pausePause or resume the job searchA
Idempotent
Inspect

Pause everything the product does on its own for 1, 3 or 6 months, or lift a pause (months=null). While paused there are no radar scans, digests, follow-ups or agent messages, and the user's own reminders wait; the resume, vacancies and history stay untouched. When the date passes, the radar runs one search and the user gets one message. It fits 'I found a job', 'not looking right now' or 'stop writing to me' without deleting the account. Instant and reversible, no quota. Returns when the pause ends (null when lifted).

Inputs: input (required). Returns: paused_until

set_vacancy_suggestion_declinedAnswer no to a tailoring questionA
Idempotent
Inspect

Record that the person answered no to a question suggestion (kind 'needs_fact') of a vacancy: the experience it asks about is not theirs, so it is not applied and the vacancy's Tailoring tab shows it as answered no. declined=false takes that answer back. Applying the suggestion later with a fact also clears it. The result lists every declined index, the same as declined_suggestion_indices in get_vacancy_detail. No quota. Errors: not_found (vacancy not theirs), invalid_payload (index out of range, not a question, or already applied).

Inputs: input (required). Returns: declined, vacancy_id, suggestion_index, declined_suggestion_indices

skip_radar_matchSkip a job matchA
Idempotent
Inspect

Skip a radar match the user is not interested in (removes it from the list and teaches the radar to rank similar vacancies lower). Applies instantly, no quota, and is reversible with undo_radar_match — which also removes the ranking signal. A match the user looked at and scrolled past in the radar feed carries the same ranking signal with status 'seen'. Returns 'not_found' if the match does not belong to the current user.

Inputs: input (required). Returns: id, status

start_radar_scanSearch job boards nowA
Idempotent
Inspect

Start a job radar scan: search job boards for vacancies matching the user's active resume. Runs asynchronously — returns a task_id immediately; the scan takes up to a minute, then get_radar_matches shows the results and get_radar_status.last_scan_at says whether it brought anything in (a scan that found nothing new leaves it as it was); get_task_status(task_id) reports progress and the outcome. Calling it while a scan is already running returns the same task_id (no double scan). Consumes one radar scan from the user's plan quota — several a day on a paid plan, one a week on the free plan, where the morning's automatic scan counts too; the account's first scan ever is not counted, and neither is a scan with changed filters after one that found nothing, while the account has never had a match. Returns 'no_resume' when the account has neither a resume nor a role named at setup, 'role_unknown' when nothing names the role to search for (no role in the radar filters or career memory, no title, position or skills on the resume; set_radar_filters stores a role), and 'limit_exceeded' when the quota is spent, naming the day it frees up. The same search as the last scan (same role, place and filters on the same resume) within an hour of it starts nothing and spends nothing: it returns 'recent_scan' with the minutes since that scan and when the same search can run again; a search with other filters (set_radar_filters) starts at once.

Inputs: no named parameters. Returns: status, task_id

start_without_resumeStart the job search without a resumeAInspect

Set up an account that has no profile yet without a resume: the job the user is looking for and, optionally, the country. The job radar turns on and its first scan runs for that role; the first scan is not counted against the radar quota, and no resume generation is spent. Afterwards get_radar_matches lists what the scan found, get_next_step names the step, and set_radar_filters changes the role or place. The account then has no resume: analyses, cover letters and tailoring answer 'no_resume' until create_profile makes the first one from resume text or five answers. country defaults to the country the account signed up from. Returns 'already_started' and changes nothing when the account was already set up this way, 'already_set_up' when it has a profile, and 'invalid_payload' for a blank role or an unknown country code.

Inputs: input (required). Returns: role, scan, status, country

translate_resumeTranslate a resumeAInspect

Translate a resume into another language as a NEW inactive copy named after the language; the original resume is not changed. Skill level and category and language name and proficiency stay fixed English keys, which the rendered resume shows in its language. Runs asynchronously — returns a task_id immediately and a message is posted into the user's chat when the copy is ready or the translation fails; get_task_status(task_id) reports progress and the outcome. Consumes one resume translation from the user's plan. If this resume was already translated into that language, returns the existing copy with status 'reused' and spends nothing. target_language is one of: en_EN, ru_RU, es_ES, pt_BR, de_DE, fr_FR, it_IT, tr_TR, hi_IN, uk_UA, id_ID, ja_JP. When the user asked for more than the translation, pass the rest as follow_up_instruction: the ready message offers it on the new copy with one tap. Returns 'not_found' if the resume does not belong to the current user, 'already_in_language' if the resume is already written in that language, 'limit_exceeded' naming the day it frees up if the plan quota is reached, and 'invalid_payload' for an unknown language code.

Inputs: input (required). Returns: status, task_id, resume_id, source_resume_id

undo_radar_matchUndo a job match decisionA
Idempotent
Inspect

Undo a verdict on a radar match: put it back in the active list after a skip, a save or a defer, and drop the ranking signal that verdict taught. A skip keeps pushing similar vacancies down until it is undone. A vacancy analysis that a save already started is NOT cancelled and its credit is not refunded. The id is the one the previous call returned. Instant, reversible, no quota. Returns 'not_found' if the match does not belong to the current user.

Inputs: input (required). Returns: id, status

update_resume_sectionEdit a resume sectionA
Destructive
Inspect

Apply an edit to one section of a resume. Editable sections: full_name, title, contacts, summary, experience, education, skills, projects, languages, interests, publications, references. Two modes, exactly one per call. ops (list sections) makes targeted add/update/remove changes addressed by the entry 'id' from get_resume; entries an op does not name stay untouched. payload replaces the whole section: an entry missing from it is removed; an entry carrying its 'id' from get_resume is matched to the stored one, and within it a key left out keeps its current value. Entry ids belong to the content_version they were read with: a call that names entries by id carries it as expected_content_version, and gets 'resume_changed' when the resume changed since. Returns the edited section with its entry ids and the new content_version; get_resume reads the whole resume. Experience dates are checked on the entries an edit adds or changes: no start in the future, no end before the start, no end date on a current role. Returns 'not_found' if the resume does not exist or does not belong to the current user, and 'invalid_payload' if the edit does not match the section shape.

Inputs: input (required). Returns: id, undo, style, title, +16 more

update_vacancy_statusUpdate a tracked job statusA
Idempotent
Inspect

Update the job-tracker status and/or notes of a tracked vacancy — e.g. mark it 'applied' after the user says they sent an application, or 'rejected' when they got a no. Statuses: new | applied | interview | offer | rejected | accepted. Status changes are recorded in the vacancy's history with the time of this call, or with occurred_at when given; setting the status it already has records nothing. notes replace the earlier notes as a whole. Returns the status before and after the call. At least one of status/notes is required. Returns 'not_found' for a missing or foreign id, 'invalid_payload' for an unknown status, an empty update, or an occurred_at that is unreadable, in the future, older than 90 days, sent without a status, or for a status that was never changed to.

Inputs: input (required). Returns: id, notes, title, status, +2 more

upsert_career_memoryUpdate career memoryA
Idempotent
Inspect

Remember or update the user's structured career preferences — target_roles, locations, remote_preference, seniority_goal, industries, salary_expectation, work_authorization, search_stage, blockers, motivation. Provided fields overwrite; omitted or null fields are kept; "" (or [] for a list) clears one. Returns the full career memory.

Inputs: input (required). Returns: facts, blockers, locations, industries, +7 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Watches company job boards (Greenhouse, Lever, Ashby, Workable, Workday and more) for new roles that match your filters, ranks them in a digest optionally fit-scored against your resume, and tracks every application with interview prep sheets. It never applies for you.
      32
      382 PyPI
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Processes and manages applicant resumes, facilitates job searches, generates job-specific resumes, and creates tailored cover letters.
      1
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Provides job search, local resume parsing, and resume-to-job matching via official APIs and local file processing.
      5
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      Enables tracking job applications through a pipeline, scheduling follow-ups, and summarizing job search progress via natural language.
      7
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.