Live Company and People Data via APIs Search, enrich, or watch a person or company in real-time. Get instant updates when an event happens.
For example, get updates when a person a) changes job or b) gets a promotion or c) adds a new skill or d) makes a new post.
This is the 4th launch from Crustdata. View more
CrustRecruiter
Launching today
Recruiting is half judgment, half grunt work. Claude brings the judgment, i.e. the reasoning and the memory, while Crustdata brings 800M+ candidate profiles and 5 recruiting skills via MCP, meaning the manual work runs itself and you get genuinely personalized recruiting at scale, all inside one chat.
Launch Team
Crustdata
Hey PH! 👋
Here's the thing about most sourcing tools. They can't actually recruit like you. You hand them a few filters, they run those filters in a black box, and they hand back a list. Every recruiter on the same tool runs the same filters and pulls the same people, which means the judgment that makes you good at this never actually makes it into the search.
We wanted to fix that, and we wanted to fix it where you already work. So we put recruiting inside Claude.
CrustRecruiter is a set of skills you install into Claude via MCP. The split is simple. Claude does the thinking, Crustdata does the manual work. Claude handles the reasoning and remembers your taste, while Crustdata handles everything that used to eat your day, like pulling profiles from 800M+ candidates, verifying emails, mapping markets, and syncing your ATS. That combination is the whole point, because once the grunt work disappears, what's left is real personalized recruiting at a scale no human sourcer could touch.
Describe a role in plain English and the whole loop runs in one chat:
🔎 Sourcing: Hand over a JD, a recorded intake call, or just describe the role, and get a ranked shortlist with a reason behind every single pick.
🗺️ Market mapping: See how big a talent pool actually is, where those people work now, and what they earn, before you commit to a search.
📇 Contact enrichment: Verified personal emails, so the list is ready to send the moment you finish reading it.
🧠 Memory: Every rejection and every "more like this" you give gets remembered, so each new search starts with the feedback from all your previous ones. Over time it sources the way you do.
✉️ Outreach + ATS: Push the shortlist into Gem or Loxo and write the outreach in your voice.
And here's the part we love. It gets better on its own. Every time Anthropic ships a stronger Claude, your recruiter gets smarter too, and you get that upgrade for free the day it lands.
Book a demo and bring a real role you're hiring for.
We'll run it with you live. crustdata.com/demo
As someone who tests AI workflows, I see so many tools that just dump data without context. The MCP integration with Claude is a smart move as it keeps the human in the loop for the reasoning, while automating the manual grunt work.
How does the 'Memory' feature handle conflicting feedback? For example, if I reject a candidate for one role but would have loved them for another, does it distinguish between role-specific taste and general taste?
Crustdata
@diana_nadim2 Hey Diana, yes it can - if you make the distinction clear for each role, Claude will be able to remember it clearly.
Lancepilot
Crustdata
@odeth_negapatan1 Yes Odeth, infact it doesn't need to 'relearn'. If users make the selection and preference distinctions for different roles clearly, it will be able to distinguish and take the right calls without having to 'relearn'
GrowMeOrganic
Congrats. As a power user of Claude, I love this! How quickly Claude adapts to recruiter feedback over multiple hiring cycles?
The real-time event tracking (promotions, job changes, new posts) is exactly what we look for in high-value intent data. Does the API integrate smoothly with standard marketing automation hubs like HubSpot, or is it strictly optimized for custom AI agents right now?
DIY UX Test
Most recruiting tools screen on keywords; teaching one to mirror my judgment on who's a fit is the harder, more useful problem. Given Crustdata's people-search roots, how much of the sourcing is live data vs. me feeding it examples of past good hires?
I have been following crustdata for a bit and this is a genuinely smart use of MCP. the part that stands out to me is the memory layer. Most sourcing tools treat every search like it's the first one you've ever done, so you're constantly re-explaining your taste. building feedback loops into the model itself is the right call.
congrats on the launch, will be sharing this with a few people in the recruiting space