convez.ai
MCP ServerProdutividadeIntermediário
trackly-app

Trackly CLI + MCP Server

trackly-app/trackly-cli

Rastreador de vagas para agentes de IA com busca semântica e recomendações

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP Server para buscar, rastrear e gerenciar candidaturas a vagas de emprego através de terminal, Claude ou ChatGPT. Acessa 128.000+ vagas em 1.900+ empresas com suporte a 40+ tipos de ATS. Integra-se nativamente a agentes de IA para automação de busca de emprego.

Instalação

$npx convez-ai trackly-app/trackly-cli

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
0
Saúde
50%
Último commit
há 4 dias
Versão
v0.29.0
Issues abertas
14
Contribuidores
1

Casos de uso

  • Buscar e filtrar vagas por função, localização, tipo de emprego e empresa
  • Rastrear candidaturas e salvar vagas de interesse diretamente via CLI ou agentes de IA
  • Análise natural de mercado de trabalho com estatísticas e briefings de empresa

Veredito

Ferramenta sólida que traduz busca de emprego em automação conversacional. Melhor valor para quem usa Claude/ChatGPT; instalação via CLI é funcional mas requer Node 18+. Cobertura de vagas é considerável, mas depende da atualização de dados do provedor.

README

A tradução para o português deste README ainda está na fila.

npm License: MIT Node 18+ MCP Server

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:

  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 18+ (LTS recommended). On macOS with the official .pkg installer, global npm installs may require sudo.

At a Glance

1,900+ companies | 128K+ jobs | 40+ ATS types | CLI + MCP | 11 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 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

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

ToolDescription
trackly_search_jobsSearch and filter jobs by function, company, location, modality, status
trackly_get_jobGet full details for a specific job
trackly_search_companiesSemantic company search
trackly_list_companiesList all tracked companies
trackly_get_statsJob tracker metrics and status counts
trackly_update_statusMark jobs as applied, saved, or dismissed
trackly_askNatural language job search (20/day)
trackly_get_job_briefGet network brief for a job (company signal, top contact, actions)
trackly_contacts_at_companySearch contacts at a specific company
trackly_get_company_workspaceFull company workspace (jobs, contacts, hiring managers, campaigns)
trackly_request_companyRequest a company be added to Trackly (rate-limited to 5 pending)

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:

  1. Sign in at usetrackly.app
  2. Go to Settings → API Keys → Create
  3. 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

FeatureCLIWeb AppPublic API
Job search + filtersYesYesYes
Apply/save/dismissYesYesYes
AI-powered searchYes (trackly ask)YesYes
MCP integrationYes (11 tools)----
Browser requiredNoYesNo
Best forTerminal + AI agentsVisual browsingCustom 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 11 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.json with 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

Ver o original no GitHub

Bom para

Relacionados