Permit MCP is an MCP server published by qinpei-dev in the Security category: stop AI agents from executing MCP tools unchecked — policy, approval, JEV decisions, and one-use execution permits.
The repository has 1 stars and 0 forks, with the last commit 18 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
✦
Ask AI about Permit MCP
Powered by Claude · Grounded in docs
I know everything about Permit MCP. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.
Releases
v0.5.0PermitMCP v0.5.0 · 29 Sep 2026PermitMCP v0.5.0 PermitMCP v0.5.0 adds a bounded integration for selected tools from one operator-configured local stdio MCP server. Existing local examples and the fixed `read_sample` upstream proof remain available. Highlights Discover…
v0.4.1PermitMCP v0.4.1 · 27 Sep 2026Security fix HTTP endpoints that execute work, modify approval state, or may consume JEV quota now require Bearer authentication. Execution and approval use separate, operator-configured tokens. Missing or identical token configuration…
v0.4.0PermitMCP v0.4.0 — Reusable ControlChain & Upstream MCP Execution · 26 Sep 2026Highlights Reusable ControlChain:** Runs deterministic policy, an optional decision provider, approval, permit issuance, and the executor in one reusable flow. Explicit decision argument projection:** An external decision provider sees…
v0.3.0Doubao-JEV-Agent v0.3.0 - Controlled Agent Execution · 24 Sep 2026Doubao-JEV-Agent v0.3.0 v0.3.0 introduces a controlled Agent execution layer that places JEV-backed decision control between proposed actions and local tool execution. Highlights Controlled Agent execution loop and `ActionProposal` model…
v0.2.1Doubao-JEV-Agent v0.2.1 - Decision Layer Hardening · 24 Sep 2026What's changed v0.2.1 focuses on reliability and engineering quality for the existing JEV-powered MCP decision layer. Reliability Centralized decision validation in the DecisionEngine. Rejects blank, duplicate, and unavailable decision…
No package has been published for this server, so install it from source: clone the repository and follow its README.
Is Permit MCP safe to use with an AI agent?
Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.
Is Permit MCP still maintained?
Yes — the latest release is v0.5.0 (29 Sep 2026), and the last commit was 18 days ago. The repository has 1 stars.