HN Hiring MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@HN Hiring MCPFind remote AI/agent engineering jobs in this month's HN hiring thread."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HN Hiring MCP
An MCP server that lets an AI agent (Claude Desktop, etc.) search the monthly Hacker News "Who is hiring?" threads for real job postings — filter by keywords and remote, get direct links.
Data comes from Hacker News' public Algolia API — no scraping, no login, no ToS issues.
Example
Ask Claude (or call the tool directly):
"Find remote or US-based AI roles paying $150k+ in this month's HN hiring thread."
→ search_jobs(roles="ai", location="remote, us", min_salary=150) returns 29 of 330
postings, each enriched and with a direct apply link:
{
"thread": "Ask HN: Who is hiring? (May 2026)",
"matched": 29,
"total_in_thread": 330,
"jobs": [
{
"headline": "Loophole Labs | Senior Systems Engineer | REMOTE (Americas & Europe) | $150k–195k USD + equity ...",
"level": ["senior"],
"location": "REMOTE (Americas & Europe)",
"stack": ["Go", "Rust", "Kubernetes"],
"salary_k": { "min": 150, "max": 195 },
"visa": false,
"company_type": ["Seed"],
"apply_url": "https://loopholelabs.io/careers",
"url": "https://news.ycombinator.com/item?id=47975670"
}
// ... 28 more
]
}Related MCP server: HN Who is Hiring Scout MCP
Tools
Tool | What it does |
| List the recent monthly "Who is hiring?" threads (id, title, date). |
| Search a month's postings. |
| Fetch ONE posting in full (the search |
| Analyze any pasted JD: returns location, tech stack, salary range ($K), visa sponsorship, company_type — funding stage (Seed / Series A–D+ / YC / Public / Bootstrapped / Profitable) or org nature (Nonprofit / Government / Academic / Agency) — and an |
| Record/update a job application (persisted to |
| List tracked applications, optionally filtered by status. |
Run locally
python -m venv .venv
./.venv/bin/pip install mcp httpx
./.venv/bin/python server.py # starts the MCP server over stdioQuick smoke test (without an MCP client):
./.venv/bin/python -c "import server; print(server.search_jobs(keywords='ai', remote=True, limit=3))"Use it in Claude Desktop
Add this to ~/Library/Application Support/Claude/claude_desktop_config.json
(use absolute paths), then restart Claude Desktop:
{
"mcpServers": {
"hn-hiring": {
"command": "/absolute/path/to/hn-hiring-mcp/.venv/bin/python",
"args": ["/absolute/path/to/hn-hiring-mcp/server.py"]
}
}
}Then ask Claude things like:
"Find remote AI/agent engineering jobs in this month's HN hiring thread."
Notes on accuracy (heuristics)
Enrichment is best-effort parsing of free-text postings, validated against a full month (330 postings):
stack — reliable (word-boundary matching;
gowon't matchgoogle).location — extracted for ~87%; some free-text formats yield
null, but thelocationfilter matches the full posting text so filtering stays reliable.salary_k — only ~28% of postings list pay. Parser ignores the
401(k)plan and non-salary numbers (100k users,50k MRR, ...).company_type — funding stage / org nature when stated; absent on many postings.
visa — means the posting explicitly states sponsorship; it does not imply others won't sponsor.
Why this exists
HN's monthly "Who is hiring?" is one of the best places to find roles at serious engineering teams — but it's a single thread of hundreds of free-text comments with no search and no filters. Finding the few postings that actually fit you (your stack, remote, salary, visa, seniority) means scrolling for ages and reading every one.
This server turns that thread into a structured, queryable dataset so a job seeker (or their agent) can pull exactly the roles that match in seconds — with the stack, salary, location, and apply link already extracted.
This server cannot be deployed
Maintenance
Related MCP Connectors
searchnapply connects your AI agent to 800K+ open jobs taken straight from company career sites, kept up to date as companies add and close them. Search in your own words with the site's filters (role, location, remote, salary, experience, department), read postings in full, and tailor a resume or cover letter from your searchnapply profile. Save a search as a monitor to collect new postings and track what you applied to or skipped. It never invents a job or a salary, and it does not apply for you: you apply on the company's own page. Free plan included, within a daily call limit.
Job platform for AI agents. Track tech jobs from companies that match your stack.
Search remote jobs from company career pages by title, location, seniority, salary, and tech stack.
Search job postings, companies, and technology stacks across 10M+ companies.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to pull live job listings from major ATS platforms (Greenhouse, Lever, Ashby, Workable), Hacker News hiring threads, and detect hiring signals on company career pages.-
- AlicenseNot gradedqualityCmaintenanceEnables agents to search Hacker News Who is Hiring posts and retrieve individual job details through standard MCP tools. It exposes read-only job discovery with keyword, location, remote, and date filters for any compatible MCP host.MIT
- AlicenseAqualityCmaintenanceEnables MCP clients to search and analyze monthly Hacker News "Who is hiring?" threads by parsing free-form job comments into structured fields such as company, role, location, work mode, salary, visa, and technologies, with tools for listing threads, searching jobs, retrieving individual posts, and viewing hiring trends.442 npmMIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search salary-transparent tech job postings across nine boards and eight countries, filter them by pay, remote work, tech stack, level, and language, and retrieve apply URLs or track applications. All commands are JSON-first, so duplicates and unfilterable criteria come back as data rather than errors.-