About Trackly CLI
Trackly CLI is an MCP server published by trackly-app in the Developer Tools category: job tracking CLI + MCP server for AI agents. 99K+ jobs, 775+ companies.
The repository has 3 stars and 0 forks, with the last commit 2 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
claude mcp add trackly-cli -- npx -y trackly-clinpx -y trackly-cliThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (57)
trackly_advance_apply_executionTransactionally create the next eligible immutable wave with frozen accessKnowledge
Parameters not published.
trackly_approve_apply_batch_resumeApprove one exact default resume for the current frozen run set
Parameters not published.
trackly_approve_apply_execution_resumeApprove one exact resume identity for an unchanged execution snapshot
Parameters not published.
trackly_askNatural language job search (20/day)
Parameters not published.
trackly_bind_apply_surfaceBind an initial or recovered browser surface to the existing run and exact requisition URL
Parameters not published.
trackly_cancel_apply_batchRetire a legacy fixed batch after explicit user confirmation
Parameters not published.
trackly_certify_apply_batch_truthCertify final answer and wording fingerprints after every other review-readiness gate
Parameters not published.
trackly_checkpoint_apply_batchBulk-record redacted inspection checkpoints and human actions
Parameters not published.
trackly_claim_apply_batchAcquire or renew a batch mutation lease
Parameters not published.
trackly_claim_apply_review_handoffClaim and classify one exact review-handoff group before reconciliation
Parameters not published.
Show all 57 tools
trackly_clear_apply_access_defermentClear one discovered user access deferment
Parameters not published.
trackly_contacts_at_companySearch contacts at a specific company
Parameters not published.
trackly_create_apply_batchFreeze an exact recent-first approved batch
Parameters not published.
trackly_defer_apply_accessPersist a job or company deferment from a Trackly jobId
Parameters not published.
trackly_diagnose_local_pathLocally diagnose the exact implicated filesystem path without deleting files
Parameters not published.
trackly_get_active_apply_batchRecover the newest unexpired active batch after context loss
Parameters not published.
trackly_get_active_apply_executionRecover the active execution before legacy batch recovery
Parameters not published.
trackly_get_application_profileGet versioned profile answers and provenance
Parameters not published.
trackly_get_apply_batchRead frozen membership with opaque pagination
Parameters not published.
trackly_get_apply_evidenceGet aggregate, value-free beta evidence and release readiness
Parameters not published.
trackly_get_apply_executionRead the authoritative progress funnel and immutable child waves
Parameters not published.
trackly_get_apply_execution_snapshotFetch a compact bounded projection for current execution members and required profile keys
Parameters not published.
trackly_get_apply_protocolGet current workflow and compatibility rules
Parameters not published.
trackly_get_apply_queueGet user-approved jobs ready for execution
Parameters not published.
trackly_get_company_workspaceFull company workspace (jobs, contacts, hiring managers, campaigns)
Parameters not published.
trackly_get_jobGet details by Trackly ID, with availability and retry guidance
Parameters not published.
trackly_get_job_briefGet a network brief, with availability and retry guidance
Parameters not published.
trackly_get_preferencesRead bounded discovery preferences, edit availability, and save revision
Parameters not published.
trackly_get_profile_onboardingGet schema plus missing questions
Parameters not published.
trackly_get_statsJob tracker metrics and status counts
Parameters not published.
trackly_lint_application_textLocally lint application writing and return only value-free violations plus a draft hash
Parameters not published.
trackly_list_apply_access_defermentsList persistent user access deferments
Parameters not published.
trackly_list_apply_review_handoffsRediscover active, value-free review-handoff receipts for one execution
Parameters not published.
trackly_list_companiesList all tracked companies
Parameters not published.
trackly_list_recoverable_apply_executionsList bounded exact-member recovery candidates after context loss
Parameters not published.
trackly_prepare_resumePrepare a private expiring resume file for upload
Parameters not published.
trackly_record_application_outcomeRecord review or confirmed submission outcome
Parameters not published.
trackly_record_application_outcomesBulk-record up to 20 leased batch outcomes with per-member conflicts
Parameters not published.
trackly_record_apply_execution_dispositionsRecord typed, value-free access classifications
Parameters not published.
trackly_record_apply_submission_evidenceRecord redacted submit-request, success-page, user-confirmation, or provider-receipt evidence
Parameters not published.
trackly_record_apply_surface_evidenceRecord current-epoch inventory, missing-tab, close-receipt, and post-close absence evidence
Parameters not published.
trackly_recover_exact_apply_membersRecover only one explicitly confirmed candidate set without substitutes
Parameters not published.
trackly_report_apply_observationSend redacted ATS mechanics feedback
Parameters not published.
trackly_report_apply_observationsBulk-send up to 20 leased, batch-bound redacted observations
Parameters not published.
trackly_request_companyRequest a company be added to Trackly (rate-limited to 5 pending)
Parameters not published.
trackly_resume_parked_apply_memberExplicitly resume one parked member for a fresh non-mutating access probe
Parameters not published.
trackly_search_companiesSemantic company search
Parameters not published.
trackly_search_jobsSearch by roles, regions, states/provinces, internship level, favorites, recency, annual USD salary floor, sponsorship, work arrangement, and pipeline status
Parameters not published.
trackly_start_apply_executionStart a target-counted accessible Apply execution
Parameters not published.
trackly_start_apply_runStart or reuse a manual-submit browser run
Parameters not published.
trackly_stop_apply_executionStop an execution without changing saved-job state
Parameters not published.
trackly_update_application_profileSave scoped answers with optimistic concurrency; revoking sensitive storage takes a two-step confirmation
Parameters not published.
trackly_update_experience_limitsAtomically replace role-specific limits on a job's stated minimum years
Parameters not published.
trackly_update_statusMark jobs as applied, saved, or dismissed
Parameters not published.
trackly_validate_apply_resume_uploadLocally validate adapter capability and ordered value-free attachment proof stages
Parameters not published.
trackly_validate_apply_tab_keep_setLocally validate an exact expected/keep tab set against complete caller-supplied inventories without controlling the browser or sending tab IDs remotely
Parameters not published.
trackly_verify_prepared_resumeRecheck the confirmed resume immediately before attachment
Parameters not published.
Ask AI
Ask AI about Trackly CLI
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
5 checks have not been run yet.
README
trackly-cli
The only job tracking CLI built for AI agents.
Search 128,000+ jobs across 1,900+ companies and 40+ ATS types. Track applications, get AI-powered recommendations, and manage your job search -- from the terminal or through Claude, ChatGPT, Cursor, and other MCP-compatible AI agents.
Two ways to connect
🚀 Option 1: One-click in Claude co-work, Claude Desktop, ChatGPT (no install)
Use Trackly directly inside your AI — zero config:
- Open Settings → Connectors → Add custom connector
- URL:
https://mcp.usetrackly.app/api/mcp - Click Add → sign in with Google → done
Full setup guide with screenshots →
Works in: Claude co-work (web), Claude Desktop, ChatGPT Connectors, and any MCP client that supports remote/streamable-http connectors.
💻 Option 2: CLI install (for Cursor, Windsurf, or terminal use)
npm install -g trackly-cli # may need: sudo npm install -g trackly-cli
trackly login
trackly jobs --function product
Prerequisites: Node.js 18+ (LTS recommended). On macOS with the official
.pkginstaller, global npm installs may requiresudo.
At a Glance
1,900+ companies | 128K+ jobs | 40+ ATS types | CLI + MCP | 10 MCP tools
CLI Commands
trackly jobs # List jobs
trackly jobs --remote # Filter remote jobs (sets usStates=REMOTE)
trackly jobs --region us # Filter by region (us, non_us, all, or a region tag: europe, canada, remote, ...)
trackly jobs --job-type internship # Filter by employment type (full_time, internship, all)
trackly jobs --function product # Filter by function
trackly jobs --company 243 # Filter by company ID
trackly job 1234 # Get job details
trackly jobs 1234 # Alias for job details
trackly companies # List companies
trackly companies search "fintech" # Semantic company search
trackly search "fintech" # Alias for semantic company search
trackly stats # Show metrics
trackly status # Alias for stats
trackly apply 1234 # Mark as applied
trackly save 1234 # Save a job
trackly dismiss 1234 # Dismiss a job
trackly ask "PM jobs in SF" # Natural language search (20/day)
trackly contacts "Stripe" # Search contacts at a company
trackly brief 1234 # Get network brief for a job
trackly referral start 1234 # Start a referral campaign
trackly referral status 1234 # Check referral campaign status
trackly company-brief 243 # Get company brief (--refresh to regenerate)
trackly company-workspace 243 # Full company workspace view
trackly api-key create # Generate API key
trackly api-key list # List API keys
trackly config # Show current CLI config
trackly config --api-key trk_xxx # Save an API key for future commands
trackly version # Show installed version
trackly whoami # Show current user
trackly logout # Clear credentials
Add --json to any command for JSON output. Use --api-key <key> or --base-url <url> as one-off global flags when needed.
MCP Server Setup
Hosted (Claude co-work, Claude Desktop, ChatGPT)
No install. In your AI tool, open Settings → Connectors → Add custom connector and enter:
https://mcp.usetrackly.app/api/mcp
Sign in with Google when prompted. Full visual guide →
Local (CLI via stdio, for Cursor / Windsurf / Claude Code)
Claude Code one-liner
claude mcp add --scope user trackly -- trackly mcp
Or equivalently:
claude mcp add-json --scope user trackly '{"command":"trackly","args":["mcp"]}'
Claude Code manual config
Add to ~/.claude/settings.json:
{
"mcpServers": {
"trackly": {
"command": "trackly",
"args": ["mcp"]
}
}
}
Cursor / Windsurf
Add to .cursor/mcp.json or ~/.cursor/mcp.json (same schema works for Windsurf):
{
"mcpServers": {
"trackly": {
"command": "trackly",
"args": ["mcp"]
}
}
}
Then use natural language in any of these clients:
- "Find me PM jobs at fintech companies"
- "What remote engineering roles are available?"
- "Mark job 1234 as applied"
MCP Tools Reference
| Tool | Description |
|---|---|
| trackly_search_jobs | Search and filter jobs by function, company, location, modality, status |
| trackly_get_job | Get full details for a specific job |
| trackly_search_companies | Semantic company search |
| trackly_list_companies | List all tracked companies |
| trackly_get_stats | Job tracker metrics and status counts |
| trackly_update_status | Mark jobs as applied, saved, or dismissed |
| trackly_ask | Natural language job search (20/day) |
| trackly_get_job_brief | Get network brief for a job (company signal, top contact, actions) |
| trackly_contacts_at_company | Search contacts at a specific company |
| trackly_get_company_workspace | Full company workspace (jobs, contacts, hiring managers, campaigns) |
Authentication
Option 1: Google OAuth (recommended)
trackly login
Opens your browser for Google sign-in. Tokens are stored locally at ~/.trackly/config.json.
Option 2: API Key
If OAuth doesn't work (firewalls, headless servers, CI), use an API key instead:
- Sign in at usetrackly.app
- Go to Settings → API Keys → Create
- Save the key:
trackly config --api-key trk_xxxxxxxxxxxxxxxxxxxx
Or pass it per-command:
trackly --api-key trk_xxxxxxxxxxxxxxxxxxxx jobs --json
Or set it as an environment variable:
export TRACKLY_API_KEY=trk_xxxxxxxxxxxxxxxxxxxx
trackly jobs
Generate a key from the CLI
If you're already logged in via OAuth, you can create a key without visiting the web app:
trackly api-key create --name "my-script"
trackly api-key list
Other config
trackly config --clear-api-key # Clear stored API key
trackly config --base-url http://127.0.0.1:3000 # Point at a different backend
Comparison
| Feature | CLI | Web App | Public API |
|---|---|---|---|
| Job search + filters | Yes | Yes | Yes |
| Apply/save/dismiss | Yes | Yes | Yes |
| AI-powered search | Yes (trackly ask) | Yes | Yes |
| MCP integration | Yes (10 tools) | -- | -- |
| Browser required | No | Yes | No |
| Best for | Terminal + AI agents | Visual browsing | Custom integrations |
Web: usetrackly.app | API docs: usetrackly.app/developers
Frequently Asked Questions
How do I track job applications from the terminal?
Install trackly-cli (npm install -g trackly-cli), authenticate with trackly login or configure an API key, then use trackly jobs to browse openings and trackly apply <id> to mark applications. All data syncs with the Trackly web app at usetrackly.app.
What MCP servers exist for job searching?
trackly-cli includes a built-in MCP server with 10 tools for job search, company lookup, and application tracking. Run trackly mcp or add it to Claude Code with claude mcp add --scope user trackly -- trackly mcp. It connects to a live database of 128,000+ jobs across 1,900+ companies.
How do I use Claude Code for job hunting?
Add trackly as an MCP server in Claude Code. Then ask questions naturally: "Find PM jobs at fintech companies in SF", "What companies are hiring for engineering?", or "Mark job 1234 as applied." Claude will use trackly's MCP tools to search and manage your applications.
What are the best CLI tools for job search?
trackly-cli is the first dedicated job tracking CLI. It provides direct terminal access to 128,000+ job postings across 1,900+ companies, with filters for job function, location, and work modality. It also integrates with AI agents via the Model Context Protocol (MCP).
Security
- OAuth tokens stored in
~/.trackly/config.jsonwith 0600 permissions - API keys can be stored in the same config file or passed per-command
- OAuth callback bound to 127.0.0.1 only
- Authenticated requests require HTTPS unless you are pointing at localhost
- HTTP requests time out instead of hanging indefinitely
- CSRF protection on login flow
- See SECURITY.md for vulnerability reporting
License
MIT -- see LICENSE
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.