Every server below was scanned with the same deterministic engine that powers the MCP Trust Checker CLI and free API. The A–F Trust Score answers one question — how safe is this server for you to adopt: it starts from the threat score of its published code, then adjusts down for the capability blast radius, how strongly the publisher is verified, and how much of the package the scan could actually see. No pay-to-list, no self-reported ratings, and every point is itemised with its evidence.
Deterministic evaluation tools for AI coding agents, exposed as an MCP server.
MCP server and library: read/write files, run commands, list files — with strict prompts for user-provided LLMs.
Local MCP server + CLI letting multiple MCP clients (Claude Code, OpenCode, Gemini CLI, …) exchange messages over a shared SQLite bus with audit logging.
Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.
MCP server bridging the Antigravity (agy), OpenAI Codex, GitHub Copilot, and Cursor CLIs so Claude Code can drive them as sub-agents
AgentKnowledgeMCP - Advanced Knowledge Management for AI Agents
595 security tests for AI agent systems - MCP, A2A, L402, x402, UCP/ACP merchant-journey, AP2 mandate + Fireblocks x402 hardening + Visa TAP / Mastercard Agentic Tokens + denial-of-settlement finality, decision governance, AIUC-1 compliance, NIST AI 800-2 aligned
通用的 AI 浏览器自动化 MCP 工具，让 AI Agent 能够以 Stealth 模式操作任意网站，兼容 agent-browser 接口
strace for AI agents. Capture and replay every tool call, LLM request, and decision point.
Minimal stdio MCP server for parallel task execution by AI agents
MCP server for any AWS AgenCore Gateway endpoint with Cognito authentication and hardware-bound token encryption
Code Knowledge Graph (CKG) engine + agent toolset, built on AgentForge.
Claude CLI transcript indexer and MCP server
Agentic Hardware-in-the-Loop (Agentic HIL) tools for AI-assisted embedded firmware loops
Model Context Protocol (MCP) Server for AI Data Privacy: LLM prompt firewall, audit logs, and 31 MCP tools for Claude, Cursor, and Windsurf.
Claude Code runner and orchestrator — thin job lifecycle, repo management, and OTEL pipeline
A tool for building and managing AI agents
Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code
Public Preview — The Secure Nervous System for Cloud-Native Agent Ecosystems - Identity, Trust, Reward, Governance
Universal MCP server that exposes coding agents (Copilot, Claude Code, Codex) as subagents via a unified tool interface
MCP server that analyzes codebases and generates AGENTS.md files
AgentSIM MCP server — OTP session tools for AI coding assistants
Decentralized multi-agent coordination MCP: claim work, survey peers, detect conflicts, and reconcile via a git branch as compare-and-swap
Control any Android phone from Claude, Cursor, or any MCP client — via ADB