From ed098f135732de4d45206a58a221cfd0d0e0d70a Mon Sep 17 00:00:00 2001 From: Radim Sekera Date: Sun, 12 Jul 2026 20:47:22 +0200 Subject: [PATCH 1/2] Add Impri (human-in-the-loop approval inbox for AI agents) Co-Authored-By: Claude Opus 4.8 --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index c1faf9613..dadb99de8 100644 --- a/README.md +++ b/README.md @@ -2767,6 +2767,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [Thezenmonster/agentscore-mcp-server](https://github.com/Thezenmonster/agentscore-mcp-server) [![agentscore-mcp-server MCP server](https://glama.ai/mcp/servers/Thezenmonster/agentscore-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/Thezenmonster/agentscore-mcp-server) 📇 ☁️ 🍎 🪟 🐧 - MCP security trust layer. Continuously monitors 800+ MCP packages on npm for install scripts, command injection, hardcoded secrets, capability drift, and publisher posture. Ships a GitHub Action policy gate for PR-level allow/warn/block decisions with OIDC auto-provisioning. 5 MCP tools, no API key required. - [tomjwxf/scopeblind-gateway](https://github.com/tomjwxf/scopeblind-gateway) [![tomjwxf/scopeblind-gateway MCP server](https://glama.ai/mcp/servers/tomjwxf/scopeblind-gateway/badges/score.svg)](https://glama.ai/mcp/servers/tomjwxf/scopeblind-gateway) 📇 🏠 — Security gateway that wraps any MCP server with per-tool policies, approval gates, and optional Ed25519-signed receipts. Shadow mode logs every tool call; enforce mode blocks, rate-limits, or requires approval. - [securityfortech/secops-mcp](https://github.com/securityfortech/secops-mcp) 🐍 🏠 - All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more. +- [sekera-radim/impri](https://github.com/sekera-radim/impri) 🎖️ 📇 ☁️ 🏠 - Human-in-the-loop approval inbox for AI agents. An agent submits a proposed action (send email, post comment, run a command) via `impri_push_action`, a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only proceeds on an approved decision. The gate is a data dependency, not a prompt. Full audit trail, self-hostable (MIT, Docker Compose). `npx @impri/mcp` - [semgrep/mcp](https://github.com/semgrep/mcp) 📇 ☁️ Allow AI agents to scan code for security vulnerabilites using [Semgrep](https://semgrep.dev). - [GUCCI-atlasv/skillssafe-mcp](https://github.com/GUCCI-atlasv/skillssafe-mcp) [![dneiil7zph MCP server](https://glama.ai/mcp/servers/dneiil7zph/badges/score.svg)](https://glama.ai/mcp/servers/dneiil7zph) 📇 ☁️ - Free AI agent skill security scanner. Scan SKILL.md, MCP configs, and system prompts for credential theft, prompt injection, zero-width character attacks, and ClawHavoc indicators. Supports OpenClaw, Claude Code, Cursor, and Codex. No signup required. - [slouchd/cyberchef-api-mcp-server](https://github.com/slouchd/cyberchef-api-mcp-server) 🐍 ☁️ - MCP server for interacting with the CyberChef server API which will allow an MCP client to utilise the CyberChef operations. From a65edc1f010060596e810278619ce13dcb55b71e Mon Sep 17 00:00:00 2001 From: Radim Sekera Date: Sun, 12 Jul 2026 22:28:38 +0200 Subject: [PATCH 2/2] Add Glama score badge for Impri --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index dadb99de8..085846e75 100644 --- a/README.md +++ b/README.md @@ -2767,7 +2767,7 @@ Tools for conducting research, surveys, interviews, and data collection. - [Thezenmonster/agentscore-mcp-server](https://github.com/Thezenmonster/agentscore-mcp-server) [![agentscore-mcp-server MCP server](https://glama.ai/mcp/servers/Thezenmonster/agentscore-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/Thezenmonster/agentscore-mcp-server) 📇 ☁️ 🍎 🪟 🐧 - MCP security trust layer. Continuously monitors 800+ MCP packages on npm for install scripts, command injection, hardcoded secrets, capability drift, and publisher posture. Ships a GitHub Action policy gate for PR-level allow/warn/block decisions with OIDC auto-provisioning. 5 MCP tools, no API key required. - [tomjwxf/scopeblind-gateway](https://github.com/tomjwxf/scopeblind-gateway) [![tomjwxf/scopeblind-gateway MCP server](https://glama.ai/mcp/servers/tomjwxf/scopeblind-gateway/badges/score.svg)](https://glama.ai/mcp/servers/tomjwxf/scopeblind-gateway) 📇 🏠 — Security gateway that wraps any MCP server with per-tool policies, approval gates, and optional Ed25519-signed receipts. Shadow mode logs every tool call; enforce mode blocks, rate-limits, or requires approval. - [securityfortech/secops-mcp](https://github.com/securityfortech/secops-mcp) 🐍 🏠 - All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more. -- [sekera-radim/impri](https://github.com/sekera-radim/impri) 🎖️ 📇 ☁️ 🏠 - Human-in-the-loop approval inbox for AI agents. An agent submits a proposed action (send email, post comment, run a command) via `impri_push_action`, a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only proceeds on an approved decision. The gate is a data dependency, not a prompt. Full audit trail, self-hostable (MIT, Docker Compose). `npx @impri/mcp` +- [sekera-radim/impri](https://github.com/sekera-radim/impri) [![sekera-radim/impri MCP server](https://glama.ai/mcp/servers/sekera-radim/impri/badges/score.svg)](https://glama.ai/mcp/servers/sekera-radim/impri) 🎖️ 📇 ☁️ 🏠 - Human-in-the-loop approval inbox for AI agents. An agent submits a proposed action (send email, post comment, run a command) via `impri_push_action`, a human approves, rejects, or edits it from a web, mobile, or Slack/Discord/Telegram inbox, and the agent only proceeds on an approved decision. The gate is a data dependency, not a prompt. Full audit trail, self-hostable (MIT, Docker Compose). `npx @impri/mcp` - [semgrep/mcp](https://github.com/semgrep/mcp) 📇 ☁️ Allow AI agents to scan code for security vulnerabilites using [Semgrep](https://semgrep.dev). - [GUCCI-atlasv/skillssafe-mcp](https://github.com/GUCCI-atlasv/skillssafe-mcp) [![dneiil7zph MCP server](https://glama.ai/mcp/servers/dneiil7zph/badges/score.svg)](https://glama.ai/mcp/servers/dneiil7zph) 📇 ☁️ - Free AI agent skill security scanner. Scan SKILL.md, MCP configs, and system prompts for credential theft, prompt injection, zero-width character attacks, and ClawHavoc indicators. Supports OpenClaw, Claude Code, Cursor, and Codex. No signup required. - [slouchd/cyberchef-api-mcp-server](https://github.com/slouchd/cyberchef-api-mcp-server) 🐍 ☁️ - MCP server for interacting with the CyberChef server API which will allow an MCP client to utilise the CyberChef operations.