Your data, your rules: how Crispy handles LinkedIn data
Most LinkedIn tools lock your data in their database. We give you three choices - managed storage, bring your own database, or fully stateless.
By Daan
Every LinkedIn automation tool on the market has the same playbook: connect to your account, scrape your data into their database, and lock you in. Your connections, messages, and profile data live on someone else's servers indefinitely. Want to leave? Good luck getting your data out.
When we built Crispy, we asked: what if you always stayed in control?
Crispy gives you three storage modes. Managed mode (the default) stores your contacts and activity data in our secure Supabase database - this powers features like Unibox, campaign tracking, and analytics. Bring Your Own Supabase (BYOS) lets you point Crispy at your own database, so your data literally never touches our servers. And stateless mode turns off all storage entirely - API call in, result out, nothing retained.
This isn't just a privacy feature. It's an architectural decision that puts you in control. Managed mode means features work out of the box. BYOS means full data ownership and portability - take your data and leave anytime. Stateless mode means zero data processing, no DPA needed, nothing to breach.
For AI agents, this flexibility is powerful. In managed mode, your agent can reference past conversations, track campaign progress, and use Unibox to manage all messages in one place. In BYOS mode, agents write directly to your infrastructure. In stateless mode, agents bring their own memory and call Crispy for real-time LinkedIn data on demand.
The only things we always store are operational necessities: your API key hash (not the key itself), your subscription status, and usage counts for rate limiting. LinkedIn credentials are never stored in any mode.
We believe this is the future of SaaS integrations: flexible data ownership where you choose the tradeoff between convenience and control. Your data, your rules.
Related articles
MCP + LinkedIn: how AI agents automate outreach
Model Context Protocol lets AI agents use LinkedIn like a human. Here's how it works and why it matters for sales teams.
The complete guide to LinkedIn MCP servers
What Model Context Protocol is, why it matters for LinkedIn automation, and how to set up Crispy as your LinkedIn MCP server in minutes.