Observed by Atlas — nobody has proved they control this domain. Is it yours?
Keydris
OBSERVEDAuthorization checks for AI agents before they act
- FRESHNESS
- 0.86
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 2
- BOT-FILTERED
- FIRST SEEN
- SEP 5
- IN THE FLOW
Keydris is authorization infrastructure that checks whether an AI agent's action is within its assigned policy before the action executes. It integrates at the boundary that carries out an action, such as MCP servers, APIs, or enterprise systems, and returns a decision of ALLOW, APPROVAL REQUIRED, or REJECT. It is aimed at platform engineers, security reviewers, and technical teams building or governing AI agents.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
Agents: 1 · Policies: 1 · Team members: 1 · KIT issuances: 1,500/month · Unlimited verification
Agents: 3 · Policies: 3 · Team members: 1 · KIT issuances: 5,000/month · Unlimited verification
Agents: 10 · Policies: 10 · Team members: 5 · KIT issuances: 25,000/month · Team administration with roles
Unlimited verification · Custom scale · Organizational governance · Enterprise administration and roles · Custom commercial terms
Every crawl is diffed. Material changes are listed.
Nobody has vouched for Keydris yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about Keydris? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it