YubHub MCP Server
YubHub MCP Server lets you manage career-page job feeds, run and schedule discovery jobs, inspect/retry jobs, and view live job-market statistics from an MCP client.
List, create, view, update, and delete job feeds from careers page URLs (optionally with an example job URL).
Show interactive dashboards for a single feed or all feeds.
Trigger feed runs and manage automatic schedules (get, enable, disable; default weekly, configurable interval).
Delete all jobs for a feed or retry failed jobs for scraping/enrichment.
List jobs by feed and status, and get detailed job information.
Read public market statistics: overview, top companies, categories, top titles, title trends, work arrangements, and experience levels.
Allows for the tracking and extraction of job listings from AMG career pages into structured, AI-enriched feeds.
Integrates with Greenhouse-hosted careers pages to automatically discover and enrich job listings into structured feeds using public APIs.
Enables the discovery and extraction of job roles from Mercedes' career pages, converting them into enriched, structured data.
Quick start
Developer docs for YubHub's API, feeds and this server are at yubhub.co/developers.
You'll need a YubHub account on the Pro Publisher plan first: the server needs an API key. Head to your account page to grab your User ID and API key (required).
Claude Desktop
Open your Claude Desktop config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add this block inside "mcpServers":
{
"mcpServers": {
"yubhub": {
"command": "npx",
"args": ["-y", "@houtini/yubhub"],
"env": {
"YUBHUB_USER_ID": "your-user-id",
"YUBHUB_API_KEY": "yh_your_api_key_here"
}
}
}
}Restart Claude Desktop. That's it. Ask Claude to "list my YubHub feeds" and you should see your data come back.
Cursor / VS Code
Same idea. Drop the config into your MCP settings and point it at npx -y @houtini/yubhub with the same env vars.
Related MCP server: Whoishiring MCP Server
What it does
YubHub watches careers pages. Point it at a company's jobs URL, and it will discover every open role, scrape the listings, enrich them with AI (title normalisation, category tagging, salary extraction, company research) and publish them as an XML feed.
This MCP server gives you full control over that pipeline from inside your AI assistant. Create feeds, trigger runs, check on jobs, view dashboards, browse market stats. No browser tab required.
The pipeline
Careers page URL
→ Discovery (ATS API / sitemap / crawl)
→ Scraping (page content extraction)
→ Enrichment (AI structuring + company research)
→ XML feed (ready for job boards, aggregators, your own site)Supported ATS platforms include Greenhouse, Lever, Workable, Workday, Oracle HCM, SmartRecruiters, Ashby, Pinpoint, Phenom and more. For platforms with public APIs (Greenhouse, Lever, Workable, Pinpoint), discovery skips scraping entirely and goes straight to enrichment.
Tools
23 tools across four areas.
Feed management
Tool | What it does |
| Get all your job feeds |
| Create a feed from a careers page URL |
| Feed details including run history and job counts |
| Interactive visual dashboard for a single feed |
| Overview dashboard with all feeds, stats and XML links |
| Start job discovery now |
| Change feed name, tag or source URLs |
| Remove a feed and all its jobs |
| Clear all jobs for a feed (keeps the feed) |
Scheduling
Tool | What it does |
| Check auto-run schedule and next run time |
| Turn on automatic runs (default: weekly) |
| Turn off automatic runs |
Jobs
Tool | What it does |
| List jobs for a feed, optionally filtered by status |
| Full job details: title, company, location, salary, skills, description |
| Re-queue failed jobs for another attempt |
Market statistics
These read the live market numbers behind yubhub.co straight into your chat. No feed and no account needed - the stats endpoints are open, so you can ask what the market's doing before you've built a thing. Ask in plain language ("which cities are hiring most?", "what's the remote-versus-onsite split?", "which titles are gaining demand?") and the server pulls the current aggregate and hands it back as a table. The same numbers power the public stats pages on the site, so what you see here is what a jobseeker sees there.
Tool | What it does |
| High-level numbers: total jobs, companies, active feeds |
| Companies ranked by job count with recent activity |
| Job counts by sector with experience level breakdown |
| Most common job titles by volume |
| Titles gaining or losing demand (2-week comparison) |
| Remote vs hybrid vs onsite distribution |
| Entry, mid, senior level distribution |
| Cities hiring most, ranked by live job count |
Environment variables
Variable | Required | Description |
| Yes | Your YubHub user ID |
| Yes | API key from your account page |
| No | API endpoint (defaults to |
Example conversation
You: Create a feed for Mercedes F1 careers at https://www.mercedesamgf1.com/careers
Claude: Done. Feed created with ID
feed_abc123. Want me to trigger a run?You: Yes please.
Claude: Discovery started. I'll check back in a couple of minutes.
You: How did it go?
Claude: Found 47 jobs. 42 enriched successfully, 5 still processing. Here's a breakdown by category...
Tip: For best results, provide an example job URL when creating a feed. This helps YubHub identify the URL pattern for job listings on that site, significantly improving discovery accuracy. You can pass it as the optional exampleJobUrl parameter in create_feed.
Development
git clone https://github.com/houtini-ai/yubhub.git
cd yubhub
npm install
npm run buildThe server compiles TypeScript to dist/ and runs as a stdio MCP server. Source lives in src/:
src/
├── index.ts # MCP server, tool definitions and handlers
├── api-client.ts # REST client for the YubHub API
├── dashboard-generator.ts # React-based interactive dashboard builder
└── types.ts # TypeScript interfacesRunning locally
YUBHUB_USER_ID=your-id YUBHUB_API_KEY=yh_your_key node dist/index.jsOr point your MCP client at the built output instead of using npx.
Contributing
Issues and pull requests welcome. If you're adding a tool or changing behaviour, please test against a real YubHub account.
Links
YubHub - the platform
Developer docs - API, feeds and MCP
Documentation - full docs
MCP specification - Model Context Protocol
License
MIT - see LICENSE for details.
Available Tools
22 toolscreate_feedC
Create a new job feed for monitoring career pages
Inputs: name (required), careersUrl (required), exampleJobUrl.
delete_feedA
Delete a feed and all associated jobs. This action cannot be undone.
Inputs: feedId (required).
delete_jobsA
Delete all jobs for a specific feed. This action cannot be undone.
Inputs: feedId (required).
disable_feed_auto_runA
Disable automatic runs for a feed. The feed will require manual triggering after this. Use this when you want full control over when a feed runs.
Inputs: feedId (required).
enable_feed_auto_runA
Enable automatic weekly runs for a feed. The scheduler worker runs hourly and will automatically trigger this feed at the configured interval (default: 7 days for weekly runs). Great for keeping job feeds updated without manual intervention.
Inputs: feedId (required), intervalDays.
get_categoriesB
Get job counts by category/sector with experience level breakdown (entry, mid, senior).
Inputs: no named parameters.
get_experience_levelsB
Get experience level distribution (entry, mid, senior, etc.).
Inputs: no named parameters.
get_feedC
Get detailed information about a specific feed including statistics
Inputs: feedId (required).
get_feed_scheduleA
Get the automatic run schedule configuration for a feed. Shows if auto-run is enabled, the run interval, and when the next automatic run is scheduled.
Inputs: feedId (required).
get_jobC
Get detailed information about a specific job
Inputs: jobId (required).
get_stats_overviewB
Get high-level statistics: total enriched jobs, companies, and active feeds.
Inputs: no named parameters.
get_title_trendsA
Get titles gaining or losing demand — compares the last 2 weeks vs prior 2 weeks.
Inputs: no named parameters.
get_top_companiesB
Get top companies by enriched job count, with recent activity (last 7d and 30d).
Inputs: no named parameters.
get_top_titlesB
Get the most common job titles by volume (top 30).
Inputs: no named parameters.
get_work_arrangementsB
Get work arrangement distribution (remote, hybrid, onsite, etc.).
Inputs: no named parameters.
list_feedsB
Get all your job feeds
Inputs: no named parameters.
list_jobsB
Get all jobs for a specific feed, optionally filtered by status
Inputs: feedId (required), status.
retry_failed_jobsA
Retry failed jobs for a feed. Jobs that failed during scraping (no content) are re-queued for scraping. Jobs that failed during enrichment (have content) are re-queued for enrichment.
Inputs: feedId (required).
show_all_feeds_dashboardB
Display a comprehensive dashboard showing all feeds with stats, sortable columns, and XML feed links. Modern React UI with dark theme.
Inputs: no named parameters.
show_feed_dashboardB
Display an interactive dashboard for monitoring a job feed
Inputs: feedId (required).
trigger_feed_runC
Start job discovery for a specific feed
Inputs: feedId (required).
update_feedB
Update a feed's name, tag, or source URLs. Use tag to group feeds by site for filtering on the dashboard.
Inputs: feedId (required), name, tag, careersUrl, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Most tools have distinct purposes, but some overlap exists: 'get_feed' and 'show_feed_dashboard' both provide feed information, and 'list_feeds' and 'show_all_feeds_dashboard' both list feeds. The descriptions clarify differences (detailed stats vs. interactive UI), but an agent might initially confuse them.
Tool names follow a consistent verb_noun pattern throughout, such as 'create_feed', 'delete_feed', 'get_categories', and 'list_jobs'. All tools use snake_case with clear, descriptive verbs, making them predictable and easy to understand.
With 22 tools, the count is borderline high for a job feed monitoring server. While it covers many aspects, it feels slightly heavy and could potentially be streamlined without losing functionality, as some tools might be combined or simplified.
The tool set provides comprehensive coverage for job feed management, including CRUD operations (create, get, update, delete), monitoring (trigger, retry, enable/disable auto-run), and analytics (stats, trends, distributions). No obvious gaps exist; agents can handle full workflows from setup to analysis.
Maintenance
Related MCP Connectors
Search live startup jobs from Claude, Cursor, or ChatGPT via MCP. Free, no account needed.
Search Thousands of jobs, Thousands of companies. MCP for Claude, ChatGPT, Codex and Cursor.
Connect Claude, Cursor, Codex, and other MCP clients to manage your Cavuno job board.
Scrape jobs from Greenhouse, Lever, Ashby, Workable, Recruitee, SmartRecruiters, Personio…
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables job search and scraping across multiple job boards (LinkedIn, Indeed, Glassdoor, etc.) with advanced filtering, directly from Claude Desktop or other MCP clients.6MIT
- FlicenseNot gradedqualityDmaintenanceEnables Claude Desktop to scan, analyze, and track job postings from Hacker News and Y Combinator's Work at a Startup using a 24-tool MCP server with multi-stage filtering and resume-based ranking.-
- AlicenseNot gradedqualityCmaintenanceEnables natural-language job search and aggregation from multiple recruitment websites with zero configuration, providing filtered results and standardized output for AI assistants.58 npmISC
- AlicenseAqualityCmaintenancePull open jobs from Workday, Greenhouse, Lever and Ashby career sites as normalized JSON with one tool call. Change tracking returns only jobs added, edited or closed since the previous run. Calls the hosted Apify Actor: set APIFY_TOKEN; tool calls are billed pay-per-event on Apify. No browser, login or proxy.1MIT