SkillFoxx

ats-mcp-server: jobs from hh.ru and ATS platforms

ats-mcp-server

An MCP server that aggregates vacancies from hh.ru and the public Greenhouse, Ashby, Lever, Workable and Bayt APIs into one format without HTML scraping

  • 1 ★ on the repository
  • Last commit
  • MIT
MCP server

Extended access

Why this level

  • A Node.js server collects jobs from ATS APIs and hh.ru, and crawls Bayt with a Playwright browser
  • Stores jobs in local SQLite and Meilisearch and sends no applications
All reasons and checks
Russian stack

alexvozhak/ats-mcp-serverAuthor:Alexvozhak

Install

Services

In your terminal, with SkillFoxx CLI

npx skillfoxx add mcp/ats-mcp-server

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • A Node.js server collects jobs from ATS APIs and hh.ru, and crawls Bayt with a Playwright browser
  • Stores jobs in local SQLite and Meilisearch and sends no applications

This is third-party code. Review the repository files before installing.

What it does

Each job source connects through its own provider behind a shared interface: four ATS platforms via their public APIs, plus two job boards, hh.ru and the Middle East board Bayt. The search_all tool searches every source at once, search_hh searches hh.ru alone, get_job_details returns a listing's details by id, get_stats computes statistics over the collected jobs, and exclude_jobs/unexclude_job hide or restore listings in results. Data is stored in SQLite, search runs on Meilisearch, and hh.ru responses use a dedicated typed Zod schema. Adding a new source, per the author, means writing one provider class.

Who it is for. For job seekers and recruiting-tool developers who want one MCP instead of scraping each job board and ATS separately.

Good fit when

  • You need to search several sources, including hh.ru, in a single query
  • You need structured job data without parsing an HTML page
  • You need to collect statistics or keep a local list of excluded listings

Not a fit when

  • You only need hh.ru: the server is broader than necessary and requires standing up Meilisearch and Docker infrastructure
  • You need resume search, applications or other hh.ru employer features: the server only searches vacancies
  • You need a stable library: part of the code sits in src/poc as experiments for individual providers

Example request

Find Python developer jobs in Moscow on hh.ru and across the international ATS sources at once

MCP

Transport
stdio
Authentication
not required

Limitations

The project is version 0.1.0 from a single author. Running it needs infrastructure: Docker Compose with Meilisearch, environment variables in .env for the sources. Some providers (Bayt) are scraped via Crawlee/Playwright rather than a pure API, which is more fragile to site changes. The provider proof-of-concept code lives in a separate src/poc folder and is not part of the main server.

How to disable. Stop the server (npm run mcp:stop or docker compose down) and remove it from your MCP client configuration.

FAQ

Can I search hh.ru only?

Yes, the search_hh tool searches hh.ru exclusively, while search_all combines every connected source.

Do I need Docker to run it?

Yes, search runs on Meilisearch, which is started with docker compose up -d alongside supporting services.

Discussion

No questions or reviews yet.

All hh.ru tools
Russian stack

An MCP server with 52 tools over the official hh.ru API: vacancy search with no token, employer resumes and applications with one, and salary statistics

MCP serverExtended access

hh.ru MCP

hh-mcp

Russian stack

MCP server for the hh.ru API: vacancy and employer search, salary estimates, reference lists, resumes with employer access

MCP serverExtended access10
Russian stack

A browser-based MCP server for job search on hh.ru: resume-matched vacancy recommendations, applications and statuses

MCP serverBroad access3
Russian stack

An hh.ru API MCP server for job seekers: vacancy search, employer data, your resumes and applications with cover letters

MCP serverBroad access39
Russian stack

An MCP server for the employer side of the hh.ru and hh.kz API: your vacancies, applications, resume search, sourcing and webhooks through an OAuth app

MCP serverBroad access1
Russian stack

An MCP server that emulates an hh.ru browser session via Playwright for search, AI vacancy scoring and automatic applications with a daily cap

MCP serverBroad access1

README in short

The README describes an MCP server that aggregates jobs from public ATS and job-board APIs, including hh.ru, without HTML scraping. It lists five MCP tools, the stack (TypeScript, Node.js 24, MCP SDK, Zod, SQLite, Meilisearch, Vitest), and setup steps via npm and Docker Compose. It separately mentions provider proof-of-concept checks under src/poc. MIT license.

README badge

Report a problem