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 30,351 packages scanned 23 categories what changed → ecosystem stats → security signals →
Delimit Cli Source verified npm
C
delimit-cli

The merge gate for AI-written code, with signed, replayable attestation. Works with Claude Code, Codex, Cursor, and Gemini CLI.

Developer Tools Score 79/100 24 findings 1.3k/wk Cap. High
Guardvibe Source verified npm
C
guardvibe

Security infrastructure your AI can't be — deterministic, current past your model's training cutoff, whole-repo-aware, author-independent. Security MCP for vibe coding. 462 rules, 39 tools, CLI + doctor. Prompt-level shift-left security (secure_prompt — e

Databases Score 79/100 22 findings 393/wk Cap. High
Servers 2 implementations
C
best: mcp-servers

Welcome to the **Hello World MCP Server**! This project demonstrates how to set up a server using the [Model Context Protocol (MCP)](https://github.com/modelcontextprotocol/typescript-sdk) SDK. It includes tools, prompts, and endpoints for handling server

Learning & Documentation Best score 79/100 2 findings 131/wk Cap. Minimal
Agent Shield npm
C
@elliotllliu/agent-shield

Multi-engine AI agent security scanner — one scan, four engines, one report

Security & Testing Score 79/100 27 findings 56/wk Cap. High
Mobile Security npm
C
mobile-security-mcp

Mobile app security analysis MCP server for Android APK and iOS IPA files

Security & Testing Score 79/100 17 findings 42/wk Cap. High
Kitty Hive Source verified npm
C
kitty-hive

MCP server for multi-agent collaboration — DM, tasks, workflow, federation

AI & Agents Score 79/100 9 findings 31/wk Cap. Critical
Brave Real Browser npm
C
brave-real-browser-mcp-server

MCP Server for Brave Real Browser - Puppeteer with Brave Browser, Stealth Mode, Ad Blocker, and Turnstile Auto-Solver for undetectable web automation.

Browser Automation Score 79/100 25 findings 30/wk Cap. High
Trash Cleaner npm
C
@childhoodandy/trash-cleaner-mcp-server

[中文 README](./README_zh.md)

Other Score 79/100 13 findings 23/wk Cap. High
Cortex npm
C
@rikaidev/cortex

Cortex AI - AI Collaboration Brain with real-time preference learning and structured thinking

Developer Tools Score 79/100 22 findings 19/wk Cap. High
Guard npm
C
@agentsid/guard

MCP server for safe shell, file, database, git, and HTTP access. Every operation validated against per-agent permission rules. Powered by AgentsID.

Security & Testing Score 79/100 18 findings 14/wk Cap. High
Thunder Eye npm
C
thunder-eye

AI gets eyes into desktop apps — MCP server for visual perception of Electron, Tauri, Flutter, Qt, and native applications

Developer Tools Score 79/100 16 findings 11/wk Cap. High
Switch Remote
C
https://mcp.switchapp.ai/mcp

Generate, manage and explore your Switch AI image and video library, scoped to your account.

Design & Media Score 79/100 6 findings Cap. High
Comfyui Source verified npm
C
comfyui-mcp

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

Communication & Collaboration Score 78/100 18 findings 142k/wk Cap. Critical
Desktop Commander Source verified 2 implementations
C
best: @wonderwhy-er/desktop-commander

Terminal and file management for the desktop: run commands, edit files and manage processes via MCP.

Files & Storage Best score 78/100 23 findings 39k/wk Cap. Critical
Context Mode npm
C
context-mode

MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.

Developer Tools Score 78/100 21 findings 18k/wk Cap. Critical
Playwright npm
C
playwright-mcp

Playwright integration for ModelContext

AI & Agents Score 78/100 3 findings 9.3k/wk Cap. High
Mneme Ai npm
C
mneme-ai

Mneme — the memory layer for your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

Analytics & Monitoring Score 78/100 19 findings 1.7k/wk Cap. High
Github npm
C
@0xshariq/github-mcp-server

A comprehensive Model Context Protocol (MCP) server that provides Git repository management capabilities for AI assistants and automation tools. Includes 29 Git operations + 11 workflow combinations with complete CLI alias system and advanced developer pr

Developer Tools Score 78/100 20 findings 192/wk Cap. High
Code Buddy npm
C
@phuetz/code-buddy

Open-source multi-provider AI coding agent for the terminal, desktop, and HTTP. 15 LLM providers (Grok, Claude, ChatGPT, Gemini, Ollama, LM Studio, …) with ~110 tools, a peer-to-peer fleet, opt-in self-improvement, multi-channel messaging, and a skills sy

Developer Tools Score 78/100 32 findings 41/wk Cap. High
Macos npm
C
macos-mcp

MCP server for controlling macOS features (volume, mail) via AppleScript

Design & Media Score 78/100 20 findings 27/wk Cap. High
Universal Command npm
C
universal-command-mcp

Cross-platform MCP server for executing shell commands on Windows and Linux

Other Score 78/100 5 findings 20/wk Cap. High
Teammcp npm
C
teammcp

MCP-native collaboration server for AI agent teams — real-time messaging, task management, and web dashboard

Productivity & Workflow Score 78/100 8 findings 12/wk Cap. Critical
Context 3 implementations
C
best: context-mcp

MCP server for project context integration - provides read-only filesystem operations for AI agents

Developer Tools Best score 78/100 3 findings Cap. High
Mcp Remote
C
https://mcp.redu.cloud/mcp

Agent-native cloud, EU-hosted. Provision VMs, networks & databases on redu.cloud via MCP.

AI & Agents Score 78/100 12 findings Cap. Critical