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.

24,072 servers 30,353 packages scanned 23 categories what changed → ecosystem stats → security signals →
Copilot Money Source verified 2 implementations
A
best: copilot-money-mcp

MCP server for Copilot Money — query personal finances locally (14 cache-mode read tools), opt into GraphQL-backed live reads with --live-reads (21 read tools: 8 cache + 13 live), and manage data via Copilot's GraphQL API (17 write tools, opt-in with --wr

Finance & Commerce Best score 92/100 4 findings 152/wk Cap. High
Jsonresume npm
A
@jsonresume/mcp

ModelContextProtocol server for enhancing JSON Resumes

Other Score 92/100 3 findings 149/wk Cap. High
Novamira Visual npm
A
novamira-visual-mcp

MCP server for connecting coding agents to Novamira Visual WordPress workspaces.

Content Management Score 92/100 1 finding 148/wk Cap. High
Elementor Mcp Agent npm
A
elementor-mcp-agent

Agentic MCP server for WordPress Elementor — multi-site management, safe Elementor data editing, template import/export, CSS flush, version tracking. Built for agencies running many client sites.

AI & Agents Score 92/100 3 findings 147/wk Cap. High
Github Mcp Custom npm
A
github-mcp-custom

Cross-platform NPX-wrappable GitHub MCP Server

Developer Tools Score 92/100 1 finding 145/wk Cap. High
Context Autopilot npm
A
context-autopilot

Automated context collection for coding agents. Watches your real agent sessions, finds what you keep repeating and correcting, and distills it into CLAUDE.md / AGENTS.md — with diffs you approve.

Developer Tools Score 92/100 2 findings 142/wk Cap. High
Kimi Webbridge npm
A
kimi-webbridge

浏览器控制工具 — 让 AI Agent 通过 CLI 或 MCP 协议操控 Chrome 浏览器

Browser Automation Score 92/100 3 findings 138/wk Cap. High
Node Code Sandbox npm
A
node-code-sandbox-mcp

Run arbitrary JavaScript inside disposable Docker containers and install npm dependencies on the fly.

Cloud & DevOps Score 92/100 10 findings 134/wk Cap. High
Sqlite Tools npm
A
mcp-sqlite-tools

MCP server for local SQLite database operations

Databases Score 92/100 1 finding 133/wk Cap. High
Weixin npm
A
weixin-mcp

MCP server for WeChat — send text, images, files, videos; receive via webhook; works with Claude Desktop, Cursor, OpenClaw

Developer Tools Score 92/100 6 findings 133/wk Cap. High
Cosmos (Polarity) npm
A
@polarity-lab/cosmos-mcp

Read and write a personal knowledge graph, the Polarity exocortex, from any LLM client.

AI, Memory & Reasoning Score 92/100 12 findings 130/wk Cap. High
Stylemcp npm
A
stylemcp

Executable brand rules for models and agents. Brand CI for AI output.

Marketing & Social Score 92/100 2 findings 128/wk Cap. High
Phasefolio npm
A
@phasefolio/mcp

PhaseFolio MCP client — biotech rNPV / probability-of-success engine for AI agents. One-line install for Claude, Codex, Cursor, and any MCP-compatible client.

Data Science & ML Score 92/100 1 finding 127/wk Cap. High
Whisper Windows npm
A
whisper-windows-mcp

Windows-native MCP server for local audio transcription using whisper.cpp with Vulkan GPU acceleration

Cloud & DevOps Score 92/100 2 findings 125/wk Cap. High
Devmind npm
A
devmind-mcp

DevMind MCP - AI Assistant Memory System - Pure MCP Tool

AI, Memory & Reasoning Score 92/100 1 finding 123/wk Cap. High
Obra Cto npm
A
obra-cto

Obra CTO: a local-first MCP that scores a codebase's Build Readiness. Your code never leaves your machine; your own Claude reads it and runs your tests. The free preview of Obra's role lineup.

Developer Tools Score 92/100 5 findings 123/wk Cap. High
Fablever npm
A
fablever

A zero-dependency working-style + discipline layer for Claude Code AND Codex CLI: scope control, evidence-grounded completion, and deterministic delivery checks. Claude Code via output style + hooks + MCP; Codex CLI via AGENTS.md + hooks + MCP + on-demand

Developer Tools Score 92/100 5 findings 122/wk Cap. High
Pagerunner npm
A
pagerunner

Persistent browser layer for AI agents. Connects any MCP client to your real Chrome profiles — already logged in, with site intelligence that compounds over time. Sessions survive daemon restarts. PII anonymization, encrypted state, auto-checkpoints, macO

Developer Tools Score 92/100 2 findings 118/wk Cap. High
Cronalert npm
A
cronalert-mcp

MCP server for CronAlert uptime monitoring — manage monitors from Claude, Cursor, or any MCP client

Analytics & Monitoring Score 92/100 2 findings 117/wk Cap. High
Labby npm
A
labby-mcp

Node launcher for Labby, a Rust homelab control plane and MCP gateway for agents, plugins, registries, and fleet operations.

Developer Tools Score 92/100 5 findings 115/wk Cap. High
Agiflowai One npm
A
@agiflowai/one-mcp

One MCP server package

Files & Storage Score 92/100 2 findings 114/wk Cap. High
Robrain npm
A
robrain

RoBrain CLI for installation, setup, and memory workflows

Databases Score 92/100 14 findings 114/wk Cap. High
Gpusmarket npm
A
gpusmarket

Rent real GPUs from the terminal. Agent-first CLI + built-in MCP server for GPUsMarket — signup, rent, chat, pool. Per-second billing, $0.50 minimum per rental.

Developer Tools Score 92/100 1 finding 112/wk Cap. High
Terminal Commander npm
A
terminal-commander

Terminal Commander: local MCP-operated terminal/file signal channel with native Linux, Windows, and macOS packages.

Developer Tools Score 92/100 11 findings 111/wk Cap. High