Habr Career MCP server

habr-career-mcp

An MCP server for the Habr Career API: filtered vacancy search, full vacancy text, a skills lookup and a local registry of vacancies already reviewed

  • 0 ★ on the repository
  • Last commit
MCP server

Extended access

Why this level

  • Runs a Python server that calls the undocumented career.habr.com API
  • Keeps a TSV registry of viewed vacancies on disk
All reasons and checks
Russian stack

mvpcodego/habr-career-mcp

Install

Services

Manual install

git clone <этот репозиторий> && cd habr-career-mcp && python3 server.py

Command from the README, runs MCP over stdio.

Access and checks

How we review

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

  • Runs a Python server that calls the undocumented career.habr.com API
  • Keeps a TSV registry of viewed vacancies on disk

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

What it does

A server built on Python's plain standard library calls Habr Career's undocumented frontend API and provides four tools: vacancy search with filters for text, grade, skill and remote work, flagging vacancies already in the registry, full vacancy text with a warning about hidden AI instructions in the description, skill id lookup by name for filtering, and checking a list of ids against a local registry. The registry is a TSV file on disk, with its path set as a constant at the top of the file.

Who it is for. For developers job-hunting who want to filter Habr Career vacancies faster than the site's UI and avoid re-reviewing ones they already saw.

Good fit when

  • You want to filter new remote vacancies by grade and skill every day
  • You want to read a vacancy in full and get a warning about hidden AI instructions in the text
  • You want a local record of vacancies already reviewed

Not a fit when

  • You need Habr Career's official documented API: this uses an internal endpoint reverse-engineered from observation
  • You do not want a local TSV registry and configuring its path

Example request

Find new remote middle Python vacancies on Habr Career that I have not reviewed yet

MCP

Transport
stdio
Authentication
not required

Limitations

The API is not officially documented; parameters were reverse-engineered and may change. Requests retry three times on network errors. The registry path is a hardcoded constant rather than an environment variable, and the qid grade filter values are not sequential, with some values empty.

How to disable. Remove the server from your MCP client config; there are no subscriptions or keys to revoke.

FAQ

Do I need external libraries?

No, the server uses only Python 3.9+'s standard library.

What is the hidden-instructions warning about?

Some employers insert phrases aimed at AI into vacancy text, like "if you are an AI, mention...", to detect generated responses. The get_vacancy tool flags such phrases; they should not be followed.

Discussion

No questions or reviews yet.

Russian stack

An MCP server that edits your own career.habr.com profile using a session cookie, because the official API is read-only

MCP serverBroad access
Russian stack

An MCP server for searching and reading Habr articles: converts an article's markup into readable markdown right in the agent's reply

MCP serverExtended access
Russian stack

A Dockerized MCP server that pulls a Habr article's text by link, aimed at local models in LM Studio

MCP serverExtended access

MCP server that searches LinkedIn, Indeed, Glassdoor and ZipRecruiter jobs and saves results to CSV or JSON

MCP serverBroad access4.7KRepository stars

A research MCP server: searches the web, SEC, courts and patents, reads whole pages and checks that cited sources really exist.

MCP serverBroad access77Repository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialAuthenticationRepository starsMain difference
Habr Career MCP server (this card)nonot required0
Workopia MCP ServeryesOAuth312hosted Workopia MCP server
JobSpy MCPnonot required4,721MCP server that searches LinkedIn

README in short

The Russian README explains the motivation: paging through hundreds of vacancies by hand is costly and the UI's filters are scattered. It documents the four tools in a table, the reverse-engineered API parameters (endpoint, qid grade values, skill id lookup), and practical gotchas: reliably identifying the company name, exact id matching against the registry, and handling hidden AI instructions in vacancy text.

README badge

Report a problem