Enterprise DNAEnterprise DNA
MMCP ServersDeveloperlow

cgrtml/reasongate

by Various

Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.

Visit siteSubmit your build →

MCP

cgrtml/reasongate

Added 23 Sept 2026

#ai-safety#explainable-ai#guardrails#jailbreak-detection#llm-guardrails#llm-security#owasp-llm#prompt-injection
Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

cgrtml/reasongate is a Python security gate for LLM applications. It blocks prompt injection attempts and provides an auditable reason for every decision. The project is open source and available on GitHub.

Best for

Best for
Developers needing an explainable prompt injection gate in Python.

Use cases

  • Add a security check before LLM inference
  • Log and audit why prompts were blocked or allowed
  • Protect LLM apps from prompt injection attacks

How to use

Install

pip install reasongate

Clients listed in this record (not verified here)

Claude Desktop, Cursor

Notes

14 stars on GitHub. Last updated 2026-09-22. Licensed Apache-2.0.

Pros

  • Provides an auditable reason for every security decision
  • Focused on a specific security concern
  • Open source and easy to inspect

Cons

  • Very early stage with only 14 stars
  • Limited community and ecosystem
  • No evidence of production readiness
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to MCP ServersSubmit your own entry →