What it does
The publisher describes sealkeep as a way for AI agents to use secrets without seeing them: secrets are injected into a command, and the output is redacted. Source details beyond this description are not available.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 16 Nov 2026 · its page on the source
sealkeep
Let AI agents use secrets without seeing them: inject into a command, redact the output.
v0.5.4As shown on registry.modelcontextprotocol.io when we last read it