에이전트가 채용 공고를 읽고, MCP 도구를 통해 요구 사항을 추출하며, 이를 이력서 프로필과 비교하여 설명과 함께 fit-score(go/no-go을 산출하고, 그 결정을 영구적인 지원 추적에 기록합니다.
전체 технический scope — архитектура, контракт MCP tools, данные схемы, план по д нижам — in SPEC.md.
This is the project skeleton after day 1: repository structure, Pydant-intic data schemas, МCP server with registered but not yet implemented tools (каждый tool call NotImplementedError and says that something needs to be rewritten). Fактуальная logicка extraction/скоринга, LапGraph-граф, tracking DB и eval-нбор — следующие шаги по плану SPEC.
Related MCP server: job-agent-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env # заполнить ANTHROPIC_API_KEYdata/resume_profile.json data with the real skills of the user is expected. The, this is a стереотип with пласихолдераим. Ot go зависит након естень адекватно fit-score.
python -m mcp_server.serverjob-tracker-agent/
├── SPEC.md # архитектура, контракты tools, план
├── mcp_server/
│ ├── server.py # регистрация MCP tools (FastMCP)
│ ├── schemas.py # Pydantic-модели
│ └── tools/
│ ├── extraction.py # fetch_job_posting, extract_job_requirements
│ ├── scoring.py # load_resume_profile, compute_fit_score
│ └── tracker.py # log_application, update_application_outcome, query_tracker_stats
├── agent/
│ ├── state.py # LangGraph state
│ └── graph.py # узлы графа (заготовка)
├── data/
│ └── resume_profile.json # заполнить своими данными
└── evals/
├── golden_cases.yaml # golden-кейсы для eval (заготовка)
└── run_eval.pyThis server cannot be deployed
Analyze job listings against your resume, track applications, and generate cover letters.
A job-search companion: tailor your CV to a role, score fit, fix ATS issues. Also via MCP.
Manage job applications — jobs, companies, boards, notes, and profile — from your AI client.
GetJobzi MCP server for job search, application tracking, and career forecasting.
