Trackly CLI MCP server

trackly-cli

The only job tracking CLI built for AI agents.

Search 250K+ jobs across 5,400+ 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:

1. Open Settings → Connectors → Add custom connector
2. URL: https://mcp.usetrackly.app/api/mcp
3. 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 20.20+ or 22.22+ (LTS recommended). On macOS with the official .pkg installer, global npm installs may require sudo.

At a Glance

5,400+ companies | 250K+ jobs | 40+ ATS types | CLI + MCP | 65 local + 62 hosted MCP tools

CLI Commands

Trackly offers three different ways to handle an application. They are never mixed up:

	What happens	How
Trackly Apply (local)	Your own AI agent (Claude in Chrome, Codex or computer use) fills the application in your browser on your computer and stops before Submit. You submit.	trackly agent setup installs the Trackly Apply (local) skill and MCP; then ask your agent to use Trackly Apply (local).
Trackly Apply (cloud)	You only request it. Trackly applies to the employer for you with your default resume (or --resume-id) and every saved profile answer, sensitive ones included, and notifies you; nothing runs on your computer. US Greenhouse, Lever and Ashby postings; each request counts toward your Trackly Apply (cloud) allowance.	trackly auto-apply <jobId>; check progress with trackly auto-apply --status. Agents use the MCP tools trackly_auto_apply and trackly_auto_apply_status.
Mark applied	You applied on your own and record it. The job also goes on your Tracker board.	trackly mark-applied <jobId> (trackly apply <jobId> does the same, for existing scripts).

trackly apply with no job ID prints this summary.

Plan response errors in --json mode emit a structured object on stdout and exit nonzero; check the exit code before treating output as a successful result.

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 --work-arrangement hybrid,remote  # Filter by work arrangement independently
trackly jobs --function product       # Filter by function
trackly jobs --sponsorship exclude_no # Visa sponsorship filter (all, exclude_no, only_yes)
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 preferences                   # Show discovery preferences and experience limits
trackly preferences experience product=2 strategy=5  # Replace role-specific limits
trackly preferences experience clear # Turn role-specific experience filtering off
trackly apply                         # How to apply with Trackly (Trackly Apply (local), Trackly Apply (cloud), mark applied)
trackly mark-applied 1234             # Record a job you applied to yourself
trackly apply 1234                    # Same as mark-applied (kept for existing scripts)
trackly auto-apply 1234               # Request Trackly Apply (cloud): Trackly applies for you
trackly auto-apply --status           # List your Trackly Apply (cloud) requests
trackly auto-apply --help             # What Trackly Apply (cloud) does, next to the other two ways
trackly save 1234                     # Save a job
trackly dismiss 1234                  # Dismiss a job
trackly ask "PM jobs in SF"           # Natural language search
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 request-company "eBay"        # Request a company be added (--url, --notes optional)
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
trackly agent setup --client both    # Install Trackly Apply (local) for Codex + Claude Code
trackly agent doctor                 # Verify setup, profile, resume, and compatibility
trackly agent diagnose-path /path/to/upload.pdf --errno ENOSPC --json  # Diagnose one exact local path

Search results set autoApplySupported to true for jobs Trackly Apply (cloud) can apply to (active US Greenhouse, Lever and Ashby postings); it does not decide Trackly Apply (local) eligibility. trackly whoami shows your plan when the server returns it. Plan refusals display server usage and reset information, plus an upgrade link only when the server provides one. Searches have no daily cap.

Add --json to any command for JSON output. Use --api-key <key> or --base-url <url> as one-off global flags when needed.

trackly preferences --json returns only success, experienceFilterV2Available, and preferences. The availability flag controls whether this client may edit role-specific limits; it does not claim that feed or alert enforcement is active. Every update checks that flag and the latest preference revision before writing.

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 →

Claude Code can use the same hosted server over OAuth:

claude mcp add --transport http trackly https://mcp.usetrackly.app/api/mcp

OAuth sign-in is the default for every client. An API key is optional and only needed for headless clients that cannot complete an interactive sign-in: send Authorization: Bearer trk_... with a key from Settings → API Keys.

Remote connections get 62 hosted tools. They share the search, company, status, Tracker, and Apply tools with the local server and add trackly_chat; the 4 local-only tools listed below are not available remotely. Hosted setup and tool details are at usetrackly.app/connector.

Trackly Apply (local) skill for Claude

If you connected Trackly from the Claude directory, the Trackly Apply (local) skill teaches Claude to finish your Apply setup and fill applications you approved in your own browser with Claude in Chrome. It stops before Submit; you always submit yourself. Each GitHub release attaches two downloads built from plugins/trackly-claude:

• trackly-apply-claude-skill-<version>.zip: upload it in claude.ai under Settings, Capabilities, Skills.
• trackly-claude-plugin-<version>.zip: a Claude Code plugin with the skill and the Claude connector. See its README to install it.

Trackly Apply (local) on the Claude connector is enabled per account while the updated directory listing is in review.

Local (CLI via stdio, for Cursor / Windsurf / Claude Code)

For agent-assisted form filling on macOS, install the public skill and local MCP together:

trackly agent setup --client codex    # or claude / both
trackly agent doctor

For an existing MCP configuration or a Cloud harness, use trackly agent setup --client both --skills-only. This installs the same checksummed skill for both native clients without invoking their MCP commands or changing authentication. CLI 0.20.1 carries universal skill 4.9.1; its policy revision is the same numeric version, superseding the personal revisions. The policy accepts a documented markHandoff() guarantee with awaited calls, exact current tab checks, and revalidation on later turns. These observations are never reported as returned persistence receipts. Browser capabilities and manual Submit remain separate requirements; installation does not make a Linux browser supported. The separately installed trackly:trackly-apply plugin is updated through its plugin manager; plugin 1.1.1 carries the same browser and profile lookup policies. This setup command does not patch plugin caches.

The skill uses the profile and default resume in your Trackly account, asks only missing questions, fills user-approved saved jobs, and always stops before Submit. “Fill the next N” continues through the original recent-first Check Later snapshot until N unauthenticated forms are durably ready for your manual review; authentication walls and exclusions are reported separately and do not consume the target. An explicit “inspect the next N records” request still uses one fixed immutable batch. Support is fetched from Trackly at the start of every run: Greenhouse is full, Ashby and Lever are best effort, and 27 additional named ATS/provider classes use constrained guided mode. Employer-hosted unknown forms run only when Trackly binds them to a verified company domain. LinkedIn-hosted forms and unverified origins remain manual-only; a separately stored external application URL is evaluated under its own ATS and origin policy.

Guided mode is deliberately fail-closed. The agent stops on credential entry, OTP/email verification, CAPTCHA/human verification, an unexpected employer or origin, a submit-only transition, or any field whose committed state cannot be observed. trackly agent doctor checks the local skill, MCP registration, protocol compatibility, declared browser/computer-use configuration, profile completeness, and default-resume metadata. Live semantic browser capability and the exact resume bytes are verified at the start of a real run.

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 a project-scoped .mcp.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"

Search filters and updates

trackly_search_jobs supports multiple roles and regions, US states and Canadian provinces, internship education levels, favorite companies, posting windows, annual USD salary floors, incremental sync, work arrangement, sponsorship and pipeline status. Exact values and examples. Search returns 20 jobs by default; request up to 100 and use offset to page.

For sponsorship, “exclude no” keeps yes and not mentioned. Use exclude_no; only_yes excludes jobs with unknown sponsorship. Ask the user when intent is ambiguous. Salary floors also keep unknown and non-comparable salaries visible. Unsupported industry/specialization/literal-search controls are rejected.

For a local server without a global package install, run npx -y trackly-cli mcp. For Codex, use codex mcp add trackly -- npx -y trackly-cli mcp; Cursor and Windsurf can use "command": "npx", "args": ["-y", "trackly-cli", "mcp"]. Authenticate with npx -y trackly-cli login first, or configure TRACKLY_API_KEY.

Existing global installs require npm install --global trackly-cli@latest. Restart the MCP process/client and refresh tool discovery after updating. For native skills and marketplace plugin updates, follow the release and update guide. Hosted and local releases are separate: the current client schema is authoritative.

MCP Tools Reference

The local stdio server (trackly mcp) registers the 65 tools below. Four are local-only because they run their checks on your machine: trackly_diagnose_local_path, trackly_lint_application_text, trackly_validate_apply_resume_upload, and trackly_validate_apply_tab_keep_set. The currently deployed hosted server has 62 hosted tools, including the five Tracker tools and the two Trackly Apply (cloud) tools.

Every tool has a family title (<Family> · <Action>), and its description starts with the family tag, for example [Tracker]. Tool names never change.

Jobs

Title	Tool	Description
Jobs · Search	trackly_search_jobs	Search by roles, regions, states/provinces, internship level, favorites, recency, annual USD salary floor, sponsorship, work arrangement, and pipeline status
Jobs · Get details	trackly_get_job	Get details by Trackly ID, with availability and retry guidance
Jobs · Ask in plain language	trackly_ask	Natural language job search

Companies

Title	Tool	Description
Companies · Search	trackly_search_companies	Semantic company search
Companies · List tracked	trackly_list_companies	List all tracked companies
Companies · Request monitoring	trackly_request_company	Request a company be added to Trackly (rate-limited to 5 pending)

Network

Title	Tool	Description
Network · Get job brief	trackly_get_job_brief	Get a network brief, with availability and retry guidance
Network · Find contacts	trackly_contacts_at_company	Search contacts at a specific company
Network · Get company workspace	trackly_get_company_workspace	Full company workspace (jobs, contacts, hiring managers, campaigns)

Preferences

Title	Tool	Description
Preferences · Get	trackly_get_preferences	Read bounded discovery preferences, edit availability, and save revision
Preferences · Set experience limits	trackly_update_experience_limits	Atomically replace role-specific limits on a job's stated minimum years

Profile

Title	Tool	Description
Profile · Get	trackly_get_application_profile	Get versioned profile answers and provenance
Profile · Get setup status	trackly_get_profile_onboarding	Get schema plus missing questions
Profile · Update answers	trackly_update_application_profile	Save scoped answers with optimistic concurrency; revoking sensitive storage takes a two-step confirmation
Profile · Check answer text	trackly_lint_application_text	Locally lint application writing and return only value-free violations plus a draft hash

Job status

Title	Tool	Description
Job status · Mark applied, saved or dismissed	trackly_update_status	Record applied, saved or dismissed on your job list. Applied also records the job on the Tracker (one entry, never a duplicate) and returns trackerEntry
Job status · Get counts	trackly_get_stats	Job tracker metrics and status counts

Tracker

Title	Tool	Description
Tracker · List entries	trackly_list_tracker_applications	List Tracker board entries by stage, company or role text, or job ID; one entry with its events by applicationId
Tracker · Add a job	trackly_create_tracker_application	Add an application to the Tracker board without duplicates, mainly one that is not a Trackly job (trackly_update_status applied already adds Trackly jobs)
Tracker · Move stage	trackly_update_tracker_stage	Move one Tracker entry to a stage (rejected, interview, offer...) with an optional dated note
Tracker · Add note	trackly_add_tracker_note	Add a dated note to one Tracker entry without changing its stage
Tracker · Undo an event	trackly_retract_tracker_event	Undo one Tracker event the user names

Trackly Apply (local)

Your own AI agent fills the form in your browser and stops before Submit; you submit.

Title	Tool	Description
Trackly Apply (local) · Get queue	trackly_get_apply_queue	Get user-approved jobs ready for execution
Trackly Apply (local) · List deferments	trackly_list_apply_access_deferments	List persistent user access deferments
Trackly Apply (local) · Defer a job, company or provider	trackly_defer_apply_access	Persist a job or company deferment from a Trackly jobId
Trackly Apply (local) · Clear a deferment	trackly_clear_apply_access_deferment	Clear one discovered user access deferment
Trackly Apply (local) · Stop a run	trackly_stop_apply_execution	Stop an execution without changing saved-job state