jev-agent-authorization
Jev agent authorization for MCP tool calls: Kinde identity and permissions plus Jev's typed, calibrated decisions, checked server-side before every call runs
How it uses Jev
Jev Gatehouse: Jev agent authorization with Kinde
Highlights
- Verifies the Kinde access token (issuer, audience, signature).
- Reads the user's permissions and feature flags for the organization, from the token or from the Kinde Management API.
- Denies the call if a Kinde permission or flag is missing. Allows reads that have the permission.
- Sends every other call to Jev with the user's request, the tool call and the documents the agent read. Jev returns calibrated signals: does the call match the request, is it destr…
- Decides in code from the signals. A low-confidence call goes to an LLM judge.
- Writes the decision to a ledger before anything runs. If the write fails, the call does not run.
- Languages
- TypeScript 96% · JavaScript 3% · CSS 1%
- License
- MIT
- Last activity
- Sep 2026
- Added
- 2026-09-24
- Stars at snapshot
- 5
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.