Jev agent authorization for MCP tool calls: Kinde identity and permissions plus Jev's typed, calibrated decisions, checked server-side before every call runs
Jev Gatehouse: Jev agent authorization with Kinde
A starter kit that checks every AI agent tool call before it runs. Kinde checks who the agent acts for and what that user can do. Jev, the System One model from TypeSafe AI, judges each call in about 200 ms. Policy code in the app decides: allow the call, ask the user to approve it, or stop it.
An agent calls a small workspace API through a Kinde MCP connection. The Kinde MCP server passes the user's access token to the API. The guard in front of the API runs these steps for each call:
1. Verifies the Kinde access token (issuer, audience, signature). 2. Reads the user's permissions and feature flags for the organization, from the token or from the Kinde Management API. 3. Denies the call if a Kinde permission or flag is missing. Allows reads that have the permission. 4. 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 destructive, does it follow planted text, does it send data out, and how risky is it. 5. Decides in code from the signals. A low-confidence call goes to an LLM judge. 6. Writes the decision to a ledger before anything runs. If the write fails, the call does not run.
A call that needs approval is held for 10 minutes. The user approves it on a page that requires a fresh sign-in. The held call then runs once.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/kinde-starter-kits--jev-agent-authorization.html)
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
TikyParkinson/mcp-agent-guardrails-spring-boot-starterSecurity & governance guardrails for MCP agents in Java — audit trail, agent-to-tool authorization, prompt-injection detection and rate limiting as a zero-config Spring Boot starter.
flankerhqd/cyvisguardSecurity control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.
adityajha2005/decisionkitFast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
abhishekswe/agent-fastpathJev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with ca
shitianfang/jev-useClaude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.