MCP Trust Registry

Add server →

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.

24,071 servers 30,352 packages scanned 23 categories what changed → ecosystem stats → security signals →
Mapx Source verified npm
B
@mgamil/mapx

Multi-language code graph memory system for LLMs

Developer Tools Score 81/100 9 findings 45/wk Cap. Critical
Msloop Source verified npm
B
msloop-mcp

MCP server for Microsoft Loop. No app registration required, uses your existing Loop web session to list workspaces and read pages.

Web, Search & Scraping Score 81/100 4 findings 35/wk Cap. Critical
Minecraft Mod Source verified npm
B
minecraft-mod-mcp

MCP server bridge & launcher CLI for Minecraft — connect AI tools to Minecraft via Model Context Protocol, launch and manage instances

Gaming & Entertainment Score 81/100 20 findings 34/wk Cap. High
Devon npm
B
@tekmidian/devon

DEVONthink MCP server for Claude Code. Zero-config setup with automatic Claude configuration.

Developer Tools Score 81/100 10 findings 31/wk Cap. High
Vibeguard npm
B
@yagyeshvyas/vibeguard

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

Developer Tools Score 81/100 42 findings 22/wk Cap. High
Architect To Product npm
B
architect-to-product

MCP server that turns software architectures into tested, secure products

Developer Tools Score 81/100 10 findings 21/wk Cap. High
Ats npm
B
ats-mcp

MCP server that lets LLMs drive ActionTestScript (ATS) — test automation across web, mobile, desktop, and API, powered by ats-core's REPL.

Security & Testing Score 81/100 6 findings 19/wk Cap. High
Eyeballs Cli npm
B
eyeballs-cli

Visual monitoring for AI agents and humans. CLI + MCP server.

Browser Automation Score 81/100 5 findings 19/wk Cap. High
Hamravesh npm
B
hamravesh-mcp

MCP server for the Hamravesh / Darkube console API — manage apps, deploys, databases, registries and billing from any MCP client (Claude, etc.).

Cloud & DevOps Score 81/100 28 findings 18/wk Cap. Moderate
Unix Disk npm
B
unix-disk-mcp

MCP server for AI-assisted disk cleanup on Unix systems (macOS and Linux)

Other Score 81/100 8 findings 18/wk Cap. High
Datamerge npm
B
@datamerge/mcp

Model Context Protocol (MCP) server for the DataMerge Company API

Business & CRM Score 81/100 4 findings 17/wk Cap. Moderate
Midas npm
B
midas-mcp

MCP server for Golden Code methodology - everything you vibecode turns to gold

Developer Tools Score 81/100 16 findings 17/wk Cap. High
Agent Quality Loop npm
B
agent-quality-loop

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.

Developer Tools Score 81/100 19 findings 15/wk Cap. High
Conductor npm
B
@useconductor/conductor

The AI Tool Hub — One MCP server. 255 tools. Every AI agent.

AI & Agents Score 81/100 23 findings 14/wk Cap. High
Sigrank npm
B
sigrank-mcp

SigRank MCP server — the yield cascade + live leaderboard as MCP tools any agent can call

Developer Tools Score 81/100 8 findings 13/wk Cap. High
Universal Ast Mapper npm
B
universal-ast-mapper

MCP server that maps source files into a normalized code skeleton (JSON + HTML) using tree-sitter.

Developer Tools Score 81/100 10 findings 13/wk Cap. High
Signal Lens npm
B
signal-lens

Context-first PR review for open-source maintainers (Skill, CLI, Action, optional MCP)

Developer Tools Score 81/100 15 findings 11/wk Cap. High
Agent Hooks npm
B
@pushary/agent-hooks

Permission hooks for AI coding agents: route tool approvals through Pushary push notifications

API Development Score 80/100 18 findings 2.8k/wk Cap. High
Code Auditor npm
B
code-auditor-mcp

Architectural invariants and code quality analysis, enforced inside your AI agent's edit loop. MCP server + CLI + Claude Code plugin. TypeScript, JavaScript, Go.

Developer Tools Score 80/100 17 findings 752/wk Cap. Critical
Mokomonitor npm
B
@mokoconsulting/mcp-mokomonitor

MCP server for server health monitoring, uptime, and log tailing

Analytics & Monitoring Score 80/100 6 findings 216/wk Cap. High
Thetacog npm
B
thetacog-mcp

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) +

Learning & Documentation Score 80/100 22 findings 192/wk Cap. High
Opscontext npm
B
@compr/opscontext-mcp

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.

AI, Memory & Reasoning Score 80/100 17 findings 126/wk Cap. High
Openchrome npm
B
openchrome-mcp

Open-source browser automation MCP server. Control your real Chrome from any AI agent.

Browser Automation Score 80/100 15 findings 114/wk Cap. Critical
Portel Ncp npm
B
@portel/ncp

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.

Web, Search & Scraping Score 80/100 21 findings 84/wk Cap. High