No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by uber · MCP Server · ★ 1.6k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ADR safe to install? View the security audit →
ADR — Agentic Detection and Response ADR is an open-source telemetry sensor and dual-agent benchmark/detection framework for securing AI agents that use the Model Context Protocol (MCP). Research artifacts for ADR: An Agentic Detection System for Enterprise Agentic AI Security (MLSys 2026). Code: github.com/uber/ADR ADR secures AI agents that use the Model Context Protocol (MCP). This repository contains the open-source ADR Sensor (telemetry) and ADR Detector (benchmark + detection framework) described in the paper. The offline ADR Explorer red-teaming engine (§3) is not included here. Repository layout §5 evaluation
| Stars | 1,574 |
| Forks | 148 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 60.5177576184094/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-19 |
| Created | 2026-04-19 |
| Platforms | claude-code, codex, mcp, python |
| Est. Tokens | ~14k |
These tools work well together with ADR for enhanced workflows:
Looking for a ADR alternative? If you're comparing ADR with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, pro
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies
MCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objecti
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucke
Explore other popular mcp server tools:
ADR is ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.. It is categorized as a MCP Server with 1.6k GitHub stars.
ADR is primarily written in Python. It covers topics such as agent-security, ai-agents, ai-security.
You can find installation instructions and usage details in the ADR GitHub repository at github.com/uber/ADR. The project has 1.6k stars and 148 forks, indicating an active community.
ADR is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to ADR on Agent Skills Hub include Adrian, cursor-talk-to-figma-mcp, Unity-MCP. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: