What they do
Safety layer controlling what coding agents can do to databases
How close to us
3, close
Blocks risky agent queries and logs everything agents touch; checks only, so W2-adjacent rather than a full agent team.
Wedges
- W2 Seeing whether your AI agents actually produce adjacent
L1 Company brain (knows the organisation) 0, none
L2 Agent team (runs agents, tools, approvals) 1, light
L3 Does and learns (finishes, checks, measures, updates the brain) 1, light
Who buys
- Firm size
- sme
- Buyer type
- developer
- Role
- head of engineering
- UK
- not known
Their own description (from YC)
Companies are connecting AI coding agents like Cursor and Claude directly to their databases — where one wrong command can delete data or leak customer records. Midplane sits in between and controls what each agent is allowed to do: it blocks dangerous queries, hides sensitive data, and keeps a record of everything the agent touches. It’s open source, and runs either as a hosted service or on your own servers.
Full teardown
No full teardown yet. On the deep list.
Technical detail
- Slug
- midplane
- Lens hash
- 179096c479
- Pass
- screen
- Stale
- no