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.
Multi-language code graph memory system for LLMs
MCP server for Microsoft Loop. No app registration required, uses your existing Loop web session to list workspaces and read pages.
MCP server bridge & launcher CLI for Minecraft — connect AI tools to Minecraft via Model Context Protocol, launch and manage instances
DEVONthink MCP server for Claude Code. Zero-config setup with automatic Claude configuration.
Security scanner + AI agent firewall. Blocks secret/PII exfiltration in real time. 752 rules, 82 MCP tools (agent-scan, mcp-audit, guard-action, generate-sbom, dep-reachability, license-compliance), AST taint analysis. Offline, zero telemetry, zero depend
MCP server that turns software architectures into tested, secure products
MCP server that lets LLMs drive ActionTestScript (ATS) — test automation across web, mobile, desktop, and API, powered by ats-core's REPL.
Visual monitoring for AI agents and humans. CLI + MCP server.
MCP server for the Hamravesh / Darkube console API — manage apps, deploys, databases, registries and billing from any MCP client (Claude, etc.).
MCP server for AI-assisted disk cleanup on Unix systems (macOS and Linux)
Model Context Protocol (MCP) server for the DataMerge Company API
MCP server for Golden Code methodology - everything you vibecode turns to gold
MCP server that guides AI agents to produce clean, policy-compliant code — runs ESLint, TypeScript, Prettier, AI security analysis (free via Groq), unused-code detection, dependency checks and more.
The AI Tool Hub — One MCP server. 255 tools. Every AI agent.
SigRank MCP server — the yield cascade + live leaderboard as MCP tools any agent can call
MCP server that maps source files into a normalized code skeleton (JSON + HTML) using tree-sitter.
Context-first PR review for open-source maintainers (Skill, CLI, Action, optional MCP)
Permission hooks for AI coding agents: route tool approvals through Pushary push notifications
Architectural invariants and code quality analysis, enforced inside your AI agent's edit loop. MCP server + CLI + Claude Code plugin. TypeScript, JavaScript, Go.
MCP server for server health monitoring, uptime, and log tailing
Geometric-Driven Development (GDD) toolkit: cognitive rooms + Shadow Agent hooks + Ghost-Read pipeline (6 routes, persona-monologue) + thetacog-iterate convergence loop (meta-rule-checker, auto-applies high-confidence rewrites, adaptive stall-softening) +
OpsContext for AI Agents — read-only fleet visibility (PM2/nginx/Docker/git/cron) + tamper-evident audit log + policy-as-code hooks. The ops + compliance layer Claude Code can't grow natively.
Open-source browser automation MCP server. Control your real Chrome from any AI agent.
Natural Context Provider (NCP) - 1 MCP to rule them all. Your MCPs, supercharged. Find any tool instantly, load on demand, run on schedule, ready for any client. Smart loading saves tokens and energy.