autoapply-mcp
An MCP server that runs a governed, human-approved job-search pipeline — from discovering and ranking postings to preparing, approving and submitting applications, then tracking outcomes.
Discover and rank jobs — fetch all configured ATS boards, apply hard gates, score survivors, and store results (
discover_jobs); filter the queue by tier, score, company, location class and pay floor (list_queue).Add new employers — probe Greenhouse/Lever/Ashby for a company's board slug (
resolve_company_board), verify and save any board including Workday (add_company_board), or mine Hacker News "Who is hiring?" threads for verified boards (scan_hiring_thread).Inspect why a job ranked — full gate result, weighted score breakdown with quoted evidence, and the posting text flagged as untrusted data (
explain_job).Prepare applications — build match reports, load employer questions and draft only profile-supported answers, selecting a resume variant (
prepare_application); add your cover letter and outstanding answers (set_application_content).Batch workflows — prepare many packets under a filter (
prepare_batch), review readiness and grouped blocking questions with a manifest hash (preview_batch), list batches (list_batches).Human-gated approval — preview the exact packet and its hash (
preview_application), approve bound to that hash (approve_application,approve_batchwith hash plus expected count).Submission — submit in manual, assisted or auto mode with all guards and pacing honored (
submit_application,submit_batch), or record one you sent yourself (record_submission).Tracking and reporting — log outcomes for conversion analytics (
record_outcome), list applications (list_applications), campaign progress and rejection reasons (campaign_status), read the redacted audit log (audit_log).Operations — reload profile, campaign and company config without restarting (
reload_config).
Integrates with Greenhouse's public job board API to discover job postings, apply eligibility gates, score candidates, and prepare applications.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@autoapply-mcp what new AI security jobs are available and which should I apply to?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
autoapply-mcp
An MCP server and local dashboard that turn a verified candidate profile into a governed job-search pipeline. It discovers postings from public ATS boards, screens out dead and ghost postings, gates and scores what survives with quotable evidence, drafts only the answers your profile supports, tailors your resume without inventing anything, refuses to submit without a recorded human approval, then follows through: it reads replies, schedules follow-ups, and helps with interviews and offers.
It is built for high-volume search without becoming a spam bot. Discovery, ranking, form-filling and bookkeeping are automated. Judgement, truthfulness and consent are not.
What it does
Stage | Behaviour |
Discover | Reads 35 kinds of employer board: Greenhouse, Lever, Ashby, Workday, SmartRecruiters, Workable, Recruitee, 12 enterprise systems (iCIMS, Taleo, SuccessFactors, Oracle Cloud, Phenom, Eightfold, Avature, Cornerstone, UKG, ADP, Paylocity, Jobvite), 12 small-business systems (BambooHR, JazzHR, Breezy, Rippling, Gem, Pinpoint, Dover, Teamtailor, Personio, HiBob, Zoho Recruit, ClearCompany) and the Google, Meta, Amazon and Apple career sites |
Source | Finds new employers: 12 job-lead sources, VC portfolio boards, Hacker News hiring threads, LinkedIn job-alert emails, funding news and a Common Crawl board harvest, each turned into a verified board before it is used |
Screen | Confirms postings are still open, clusters reposts, flags ghost-posting signals, and honours your do-not-apply list and dismissed postings |
Gate and score | Hard-rejects on location, seniority, pay floor, clearance, citizenship and sponsorship, then ranks survivors on seven weighted dimensions, each with the quote that earned it |
Evaluate | Builds a deep, scored report for a posting (fit, gaps, level, compensation, legitimacy) that you or your agent can save and compare |
Draft | Loads the employer's real questions and answers only what verified profile data supports |
Tailor | Renders a one-page resume tailored to each posting from your |
Approve | Binds a human approval to a hash of the exact submission content |
Submit | Manual, assisted or auto, never beyond the mode the campaign permits |
Follow through | Reads replies (read-only), records outcomes you confirm, drafts follow-ups, closes ghosted applications, exports a tracker and reports what is working |
Interview and offer | Story bank, interview preparation and debriefs, contacts and outreach drafts, offer comparison and negotiation plans |
Orchestrate | A run queue for long jobs and a local dashboard to start runs, watch them, and see where every job and application stands |
Related MCP server: jobjourney-claude-plugin
Design rules
Nothing is invented. Every drafted answer traces to a profile field or a pre-approved answer, tailoring only reorders content already in your resume source, and cover letters and outreach are fact-checked. Anything else is handed back to you.
Sensitive questions always stop. Work authorization, citizenship, compensation, criminal history, demographics and legal attestations require a human decision by default.
Approval binds to content.
approve_applicationrecords a packet hash. Editing anything invalidates it and submission is refused.External text is untrusted data. Job descriptions, careers pages, emails and lead sources are scanned for prompt-injection patterns, wrapped in an explicit data boundary, and never treated as instructions. Every URL is checked before it is fetched, including what its host name resolves to, so a link cannot reach your own network.
Anti-bot controls and terms are respected. A detected CAPTCHA aborts the run and hands the application back to you; there is no solving, evading or fingerprint spoofing. Sources whose terms forbid automated access stay off unless you enable them.
Destinations are allowlisted. Submissions only go to hosts and companies the campaign explicitly trusts, over HTTPS.
It never speaks for you. The server reads your mailbox but never sends email or messages. Follow-ups and outreach are drafts for you to send, and replies are recorded only when you confirm them.
Requirements
Node.js 22.5 or newer (uses the built-in
node:sqlite, so there is no native build step)Playwright for assisted or automatic form filling, and for rendering tailored resumes:
npm install playwright && npx playwright install chromium
Install
git clone <repository-url> autoapply-mcp
cd autoapply-mcp
npm install
npm run build
npm testConfigure
Personal data lives outside the repository, so a checkout can be published as-is. The default home is ~/.autoapply:
npm run initinit creates ~/.autoapply from the shipped examples, adds resumes/, data/ and artifacts/, and prints the editing order. It never overwrites a file that already exists, so it is safe to re-run. Your agent can then fill the profile in conversation with the onboard prompt and the profile_status, update_profile and import_resume_text tools; see docs/ONBOARDING.md.
The profile template
examples/profile.example.json holds no personal data, compensation or location preferences. It does carry a bank of 170 recurring application questions, each matched to the wordings employers use:
Fill in:
identity,workAuthorization,compensation,preferences,resumes,skills,facts,experienceandeducation. Every value in these sections is a placeholder or an example to replace. TheworkAuthorizationcountry lists start empty, which gates out every posting that requires citizenship until you add the ISO codes, such asCAorUS, of the countries you can work in.Pre-answered: decisions that hold for almost anyone, which you should review once before your first run: "How did you hear about us?" (the company careers page), privacy, data-processing and background-check consents, and voluntary demographic questions, set to decline.
Blank: anything personal. A blank answer means you are asked whenever a form needs it; write it once and it is reused. Legally material questions, such as work authorization, export control, government ties, arbitration and salary, are also set to
allowAutoFill: false, so a filled-in answer stays a suggestion until you set it to true.Narratives: the "why this company" templates stay suggestions until you rewrite them in your own words and set
allowAutoFillto true. See docs/BATCH.md.
For tailored resumes, write ~/.autoapply/resume.json from examples/resume.example.json and set documents.tailorResume; see docs/DOCUMENTS.md.
Then verify:
node dist/cli/doctor.js --probedoctor validates all three files, checks that your resume files exist and are real PDFs, confirms every track points at a resume variant, warns about settings written in the wrong place, and probes each configured board. Unknown keys are stripped silently by the schema, so a setting written one level too high reads as configured and behaves as absent; doctor reports these as WARN and names where the setting belongs.
presets/ai-security-us-canada.json ships 135 company boards verified live against the ATS APIs, weighted toward AI, security and infrastructure companies in the US and Canada. It is a starting point: add boards with resolve_company_board and add_company_board, or let propose_companies suggest verified ones from your leads.
A fresh install cannot contact an employer: submission.mode is manual, and submission.allowedCompanies is empty, which blocks every company until you add it by name.
Every setting and environment variable is described in docs/CONFIGURATION.md.
Register with an MCP client
{
"mcpServers": {
"autoapply": {
"command": "node",
"args": ["/absolute/path/to/autoapply-mcp/dist/index.js"],
"env": { "AUTOAPPLY_HOME": "/absolute/path/to/your/.autoapply" }
}
}
}The server speaks stdio and logs to stderr, so stdout stays clean for the protocol. Configuration for Copilot CLI, VS Code, Claude Desktop, Claude Code and others is in docs/CLIENTS.md.
It registers 95 tools in eight toolsets: core, sources, screening, documents, followup, career, onboarding and runs. Some clients cap the tools one request may carry (VS Code allows 128 across all servers), so load only what you use, for example "AUTOAPPLY_TOOLSETS": "core,screening,followup". Guided workflows ship as MCP prompts, starting with autoapply_guide.
The dashboard
npm run dashboard # serves http://127.0.0.1:4317 and prints a sign-in linkA local web app over the same services as the tools: start discovery, preparation, submission and sourcing runs and watch them live; review the queue, dismiss postings, and approve exact packets; work through replies, follow-ups, interviews and offers; and check analytics, sources and system health. It only listens on loopback and every request needs the session token. See docs/DASHBOARD.md.
Typical session
Single application:
discover_jobs -> fetch every board, gate, score, store
list_queue -> the ranked, de-duplicated shortlist
evaluate_job jobId -> a deep report: fit, gaps, level, pay, legitimacy
prepare_application jobId -> liveness check, match report, employer questions, drafted answers, tailored resume
set_application_content -> your cover letter and any answers only you can give
preview_application -> the exact packet plus its hash
approve_application + hash -> your explicit authorization
submit_application mode -> manual, assisted or auto
record_outcome -> or let scan_inbox propose it from the replyHigh volume:
prepare_batch {tiers:["A","B"], locationClasses:["bay-area"], minCompensation:250000}
preview_batch -> the set, plus grouped blocking questions
approve_batch + manifestHash + expectedCount
submit_batch mode -> honours configured limits and pacingLong jobs such as a full discovery or a paced submission round also run in the queue (start_run, or the dashboard), where they survive client timeouts.
Submission modes
Mode | Behaviour | Use it when |
| Server prepares the packet; you submit it yourself | Always start here |
| Server fills the hosted form in a visible browser and leaves it open for you to review and submit | After the manual pilot proves the packets are right |
| Server fills and clicks submit | Only for allowlisted companies on forms you have already seen work |
Browser submission covers Greenhouse, Lever, Ashby, Workday and the Google, Meta and Amazon career sites. The other ATS kinds are discovery-only and produce manual packets. auto additionally requires the company to appear in submission.allowedCompanies, every required field to be fillable, and no blocked questions to remain unanswered.
What it deliberately does not do
No LinkedIn, Indeed or Wellfound automation. Their terms prohibit it and signing in would put your account at risk. Their job-alert emails can be imported as leads; apply through the employer's own board.
No sending. It never sends email, LinkedIn messages or follow-ups; it drafts them for you.
No CAPTCHA solving, proxy rotation or fingerprint evasion.
No invented content. The server supplies structured evidence and fact-checks; your agent writes the words and you approve them.
Known limitations
Compensation parsed from description text is a heuristic. Postings that list several geographic pay zones can yield the wrong figure, so those results carry a
compensation-parsed-from-textflag. Structured ATS pay data is preferred whenever a board publishes it.FX rates in
campaign.jsonare static. Update them before relying on a cross-currency floor.Only Greenhouse publishes an application question schema. For other boards the server drafts against a baseline field set and reads the real form during an assisted run.
Enterprise and small-business boards cannot all be found by guessing; some must be added from the careers URL. Their formats and caps are in docs/SOURCES_ENTERPRISE.md and docs/SOURCES_SMB_AND_LEADS.md.
@modelcontextprotocol/sdkcurrently pulls a transitive advisory in@hono/node-serveraffecting its static-file server. This server uses the stdio transport only and never serves files through it, so the affected code path is not reachable.
Documentation
Document | Covers |
Every tool and prompt, generated from the live schemas | |
profile.json, campaign.json, companies.json and environment variables | |
Registering the server with each MCP client | |
Setting up a profile and campaign in conversation | |
Boards, lead sources, formats, limits and terms | |
Finding new employers: alerts, funding news, proposals and the Common Crawl harvest | |
Liveness, reposts, legitimacy, the do-not-apply list and deep evaluation reports | |
resume.json, tailored resumes, cover letters and fact checks | |
High-volume campaigns and cached personal data | |
Inbox replies, follow-ups, outcomes and analytics | |
Story bank, interviews, contacts, outreach and offers | |
The dashboard and the run queue | |
Moving your workspace to another machine or a cloud sandbox | |
The guarantees and their limits |
Development
npm run typecheck
npm test
npm run coverage
node scripts/check-no-user-data.mjsNearly 3,400 tests cover every adapter against recorded fixtures, the gates and scoring, the answer policy, submission guards and packet hashing, the run queue, the dashboard API, the after-apply loop, document tailoring and an end-to-end run through a real in-memory MCP client. npm run typecheck checks the tests as well as the source, and unit tests never touch the network. CI runs both on Linux and Windows and fails if a tracked file looks like personal data.
docs/TOOLS.md is generated from the tool schemas; after changing a tool, regenerate it with UPDATE_TOOL_DOCS=1 npx vitest run test/toolDocs.test.ts.
Credits
Several features (posting liveness and legitimacy checks, deep evaluations, the story bank, interview and offer workflows, follow-up cadence, and many source adapters) adapt ideas and code from career-ops under the MIT License. See THIRD_PARTY_NOTICES.md.
License
MIT
Available Tools
22 toolsadd_company_boardVerify and save a company's boardA
Checks that a candidate board actually serves postings, then saves it to companies.json. Nothing is saved unless postings were seen, because a wrong slug often answers 200 with a generic page rather than an error. Use this to record boards found elsewhere — a careers-page URL or a web search — including Workday, which cannot be probed by guessing.
Inputs: ats (required), name (required), board (required), save, +4 more.
approve_applicationApprove an application for submissionA
Records the human decision that authorizes submission. The supplied packetHash must match the current content exactly; any later edit invalidates the approval.
Inputs: packetHash (required), applicationId (required), note, decision.
approve_batchApprove every ready application in a batchA
Records a human approval for each ready application in the batch. Requires the current manifest hash and the exact count being approved, so approval cannot silently cover more applications than were reviewed.
Inputs: batchId (required), manifestHash (required), expectedCount (required), note.
audit_logRead the audit logARead-only
Returns recent recorded events: discovery runs, approvals, submissions and blocked attempts. Values are redacted.
Inputs: type, limit.
campaign_statusCampaign status and metricsARead-only
Summarizes progress toward the application target, pipeline health, tier distribution and the most common rejection reasons.
Inputs: no named parameters.
discover_jobsDiscover and rank jobsA
Fetches every configured ATS board, normalizes the postings, applies the campaign's hard gates, scores what survives, and stores the results. Read-only against employers: no application is created or sent.
Inputs: companies, includeIssues.
explain_jobExplain a job evaluationARead-only
Returns the full gate result, score breakdown with quoted evidence, and the posting text wrapped as untrusted data.
Inputs: jobId (required), includeDescription.
list_applicationsList applicationsCRead-only
Lists applications with their status, target role and outcome history.
Inputs: limit, status.
list_batchesList prepared batchesBRead-only
Recent batches with their status and per-state counts.
Inputs: limit.
list_queueList the ranked application queueARead-only
Returns gated-in jobs ordered by score. Roles already applied to are excluded by fingerprint, so the same posting on a second board is not surfaced twice.
Inputs: limit, tiers, trackId, minScore, +5 more.
prepare_applicationPrepare an application packetA
Builds the match report, loads the employer's application questions, drafts only the answers that verified profile data supports, and selects the resume variant for the matched track. Creates a local draft; nothing is sent.
Inputs: jobId (required), force.
prepare_batchPrepare many applications at onceA
Selects queued jobs matching a filter and prepares an application packet for each, using the same drafting and validation as the single-job path. Creates local drafts and a batch manifest; nothing is sent. Applications whose questions still need a human decision are marked needs_human and excluded from batch approval. The campaign's submission.maxBatchSize is a hard ceiling, so a larger limit is silently reduced to it.
Inputs: limit, tiers, minScore, trackIds, +4 more.
preview_applicationPreview exactly what will be submittedARead-only
Renders the full submission packet - every field, its value and where the value came from - plus the packet hash to approve.
Inputs: applicationId (required).
preview_batchReview a prepared batchARead-only
Lists every application in a batch with its company, role, resume variant and readiness, plus the grouped questions blocking the rest. Returns the manifest hash required to approve.
Inputs: batchId, includeReady.
record_outcomeRecord an application outcomeA
Appends an outcome to an application's history so conversion rates can be measured per track, tier and company.
Inputs: status (required), applicationId (required), detail.
record_submissionRecord a manual submissionA
Marks an application as submitted after a person sent it, so counts, pacing and duplicate checks stay accurate.
Inputs: applicationId (required), notes, confirmationRef.
reload_configReload configurationA
Re-reads profile.json, campaign.json and companies.json so edits take effect without restarting the server.
Inputs: no named parameters.
resolve_company_boardFind a company's ATS boardARead-only
Probes Greenhouse, Lever and Ashby for a company's public board slug. Board tokens are not published centrally, so guesses must be verified before being added to companies.json. Workday is not probed: its tenant, datacenter and site slug cannot be guessed, so find that URL on the employer's careers page and record it with add_company_board.
Inputs: companyName (required), extraSlugs.
scan_hiring_threadFind new boards from Hacker News 'Who is hiring?'A
Scans a monthly Hacker News 'Ask HN: Who is hiring?' thread for links to employers' own ATS boards, verifies each one actually serves postings, and optionally saves the new ones to companies.json. This is a lead source, not a job source: the thread's prose cannot be gated on reliably, so only the board slug is taken and discover_jobs then ingests every role at that company with full structured pay and location. Free to call — it uses the public Hacker News API and no third-party scraping credits.
Inputs: save, tier, limit, threadId.
set_application_contentSet cover letter and outstanding answersA
Records a cover letter and answers to questions the policy engine would not fill on its own. Changing content invalidates any prior approval, because approval is bound to the packet hash.
Inputs: applicationId (required), notes, answers, coverLetter.
submit_applicationSubmit an approved applicationADestructive
Runs every submission guard, then acts according to mode. 'manual' returns the packet for a person to submit. 'assisted' fills the hosted form in a visible browser and leaves it for a person to submit. 'auto' fills and clicks submit, and is only available when the campaign and company allowlists permit it.
Inputs: applicationId (required), mode, headless, keepOpenSeconds, +2 more.
submit_batchSubmit an approved batchADestructive
Submits every approved application in the batch, re-running all per-application guards for each one and honouring the daily limit and pacing delay. Stops cleanly when the daily limit is reached so the rest can continue on the next run. The campaign's submission.maxBatchSize also caps how many are submitted per run.
Inputs: batchId (required), mode, headless, maxSubmissions.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Each tool targets a distinct stage of the auto-apply pipeline—discovery, scoring, preparation, approval, submission, or tracking—with clear separation between single and batch operations (e.g., prepare_application vs. prepare_batch). The related board-probing and saving tools (resolve_company_board, add_company_board, scan_hiring_thread) are clearly differentiated by their input source and purpose. No two tools appear to perform the same action on the same resource.
The overwhelming majority of tools follow a consistent verb_noun pattern (discover_jobs, prepare_application, approve_batch, etc.). Two tools, campaign_status and audit_log, use noun forms without an explicit verb, slightly deviating from the otherwise uniform convention. Overall the pattern is highly predictable and readable.
With 22 tools, the server is on the heavier side of the typical range, but each tool maps to a necessary operation in the end-to-end job application workflow. The many batch and single variants double the count, yet they serve distinct use cases (individual review vs. bulk processing). The size feels justified for the scope, though it is not minimal.
The tool set provides full lifecycle coverage from board discovery to outcome recording, including preparation, approval, submission, batch handling, and monitoring. Administrative tools for configuration reload and audit logging round out the surface. There are no obvious dead ends; agents can compose these tools to simulate the entire auto-apply process.
Maintenance
Related MCP Connectors
Public MCP server for discovering open jobs. Search, filter, and get application links.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Job application tracker for developers - AI agents write over MCP, you review in a dashboard.
GetJobzi MCP server for job search, application tracking, and career forecasting.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceMCP server for job search and application tracking, enabling AI agents to search jobs, get details, manage applications, and find contacts across 128K+ jobs and 1,900+ companies.1,315 npm3MIT- AlicenseCqualityCmaintenanceAn MCP server that enables AI-assisted job search workflows including job discovery, application tracking, resume evaluation, and cover letter generation, with support for multiple job sources and scheduled scraping.8356 npm1AGPL 3.0
- AlicenseBqualityBmaintenanceMCP server for job search, enabling profile creation, job hunting, review, and supervised application preparation without auto-submission.41Apache 2.0
- AlicenseNot gradedqualityCmaintenanceAn MCP server that exposes job-search and application-management capabilities to compatible AI clients, enabling discovery of vacancies, drafting of tailored application materials, and coordinated human-approved submissions.MIT