From 5e58b12bcef02e4c2ba24a446623ee13e823351f Mon Sep 17 00:00:00 2001 From: rexrubyai Date: Wed, 3 Jun 2026 13:29:09 -0700 Subject: [PATCH] Add EMILIA Protocol (human sign-off + trust receipts for AI agents) Adds @emilia-protocol/mcp-server under Security. Co-Authored-By: Claude Opus 4.8 (1M context) --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 0cd64e03b..4003bd32b 100644 --- a/README.md +++ b/README.md @@ -2304,6 +2304,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [cyntrisec/cyntrisec-cli](https://github.com/cyntrisec/cyntrisec-cli) 🐍 🏠 - Local-first AWS security analyzer that discovers attack paths and generates remediations using graph theory. - [dkvdm/onepassword-mcp-server](https://github.com/dkvdm/onepassword-mcp-server) - An MCP server that enables secure credential retrieval from 1Password to be used by Agentic AI. - [duriantaco/skylos](https://github.com/duriantaco/skylos) [![mcp-skylos MCP server](https://glama.ai/mcp/servers/@duriantaco/mcp-skylos/badges/score.svg)](https://glama.ai/mcp/servers/@duriantaco/mcp-skylos) 🐍 🏠 🍎 🪟 🐧 - Dead code detection, security scanning, and code quality analysis for Python, TypeScript, and Go. 98% recall with fewer false positives than Vulture. Includes AI-powered remediation. +- [emiliaprotocol/emilia-protocol](https://github.com/emiliaprotocol/emilia-protocol) 📇 🏠 - Human sign-off + trust receipts for AI agents: requires a named human's approval before an irreversible action (payment release, record change, deploy), then mints an offline-verifiable Ed25519 Trust Receipt. Also exposes trust profiles, receipt verification, disputes, and delegation. Apache-2.0; policy engine formally verified. Install: `npx -y @emilia-protocol/mcp-server`. - [Erodenn/fetch-guard](https://github.com/Erodenn/fetch-guard) [![fetch-guard MCP server](https://glama.ai/mcp/servers/@Erodenn/fetch-guard/badges/score.svg)](https://glama.ai/mcp/servers/@Erodenn/fetch-guard) 🐍 🏠 🍎 🪟 🐧 - URL fetcher and HTML-to-markdown converter with three-layer prompt injection defense: pre-extraction sanitization of hidden/off-screen elements and non-printing Unicode, 15-pattern risk scanning (HIGH/MEDIUM/OK), and per-request session-salt content boundary wrapping. - [firstorderai/authenticator_mcp](https://github.com/firstorderai/authenticator_mcp) 📇 🏠 🍎 🪟 🐧 – A secure MCP (Model Context Protocol) server that enables AI agents to interact with the Authenticator App. - [forest6511/secretctl](https://github.com/forest6511/secretctl) 🏎️ 🏠 🍎 🪟 🐧 - AI-safe secrets manager with MCP integration. Run commands with credentials injected as environment variables - AI agents never see plaintext secrets. Features output sanitization, AES-256-GCM encryption, and Argon2id key derivation.