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 →
Settlemint Sdk Source verified npm
B
@settlemint/sdk-mcp

MCP interface for SettleMint SDK, providing development tools and project management capabilities

Developer Tools Score 88/100 4 findings 1.6k/wk Cap. High
Universal Netlist Source verified npm
B
@intelligentelectron/universal-netlist

MCP server for netlist parsing and circuit analysis

Developer Tools Score 88/100 5 findings 1.3k/wk Cap. High
Wigolo Source verified npm
B
wigolo

Local-first web intelligence MCP server for AI coding agents

Web, Search & Scraping Score 88/100 15 findings 1.3k/wk Cap. High
Nebula Notebook Source verified npm
B
nebula-notebook-mcp

MCP server for Nebula Notebook — lets agents (Claude Code, Codex, etc.) read, edit, and execute notebooks on a running Nebula server

Data Science & ML Score 88/100 2 findings 1.3k/wk Cap. High
Agency Orchestrator Source verified npm
B
agency-orchestrator

Multi-agent YAML workflow engine — 267 CN + 184 EN + 5 more language libraries of AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 11 LLM providers, 7 need no API key.

Developer Tools Score 88/100 11 findings 743/wk Cap. High
Puppeteer for Claude Source verified 2 implementations
B
best: puppeteer-mcp-claude

Puppeteer-powered browser automation built for Claude.

Browser Automation Best score 88/100 2 findings 711/wk Cap. High
Sverklo Source verified npm
B
sverklo

Local-first repo-memory MCP for coding agents. Best for relationship-heavy edits: symbols, callers, dependencies, diff review, and git-pinned decisions before code changes. Start with a no-write proof receipt; use grep/ripgrep for exact strings. MIT; bund

Web, Search & Scraping Score 88/100 15 findings 448/wk Cap. High
Stifler Memex Source verified npm
B
stifler-memex-mcp

Developer context continuity system — temporal knowledge graph for AI coding agents via MCP. Inspired by Vannevar Bush's 1945 concept of a machine that remembers everything.

AI, Memory & Reasoning Score 88/100 2 findings 447/wk Cap. High
Neotoma Source verified npm
B
neotoma

MCP server for structured personal data memory with unified source ingestion

AI, Memory & Reasoning Score 88/100 14 findings 431/wk Cap. High
Crosspad Source verified npm
B
crosspad-mcp-server

MCP development server for CrossPad — build, test, manage apps, interact with simulator

Developer Tools Score 88/100 12 findings 403/wk Cap. High
Figma Ui Source verified npm
B
figma-ui-mcp

Claude Code to Figma — Bidirectional MCP bridge. AI draws UI on Figma canvas, reads designs back. Works with Claude, Cursor, VS Code, Windsurf, Antigravity. No API key needed.

Design & Media Score 88/100 3 findings 375/wk Cap. High
Q Ring Source verified npm
B
@i4ctime/q-ring

Quantum keyring for AI coding tools — Cursor, Kiro, Claude Code. Secrets, superposition, entanglement, MCP.

Security & Testing Score 88/100 8 findings 331/wk Cap. High
Claude Code Organizer Source verified npm
B
@mcpware/claude-code-organizer

Organize all your Claude Code memories, skills, MCP servers, commands, agents, rules, and hooks — see what loads globally vs per-project, then move items between scopes

Developer Tools Score 88/100 9 findings 275/wk Cap. High
Cdpilot Source verified npm
B
cdpilot

Zero-dependency browser automation CLI. Raw CDP, 60+ commands, stealth + adaptive escalation, CAPTCHA solvers, proxy pools, TLS probe, MCP server. No Puppeteer/Playwright/Selenium.

Browser Automation Score 88/100 3 findings 266/wk Cap. High
Yomi Source verified npm
B
@rikaidev/yomi

Open-source personal LINE MCP server for AI agents. Read, reply, send images, and search LINE conversations locally with Letter-Sealing E2EE.

Web, Search & Scraping Score 88/100 5 findings 209/wk Cap. High
Tankpkg Source verified npm
B
@tankpkg/mcp-server

MCP server for Tank - scan and publish AI agent skills from your editor

Content Management Score 88/100 4 findings 208/wk Cap. High
Brutalist Source verified npm
B
@brutalist/mcp

Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation continuation & intelligent pagination.

Learning & Documentation Score 88/100 4 findings 207/wk Cap. High
Envcp Source verified npm
B
@fentz26/envcp

MCP server for secure environment variable management - Keep your secrets safe from AI agents

Security & Testing Score 88/100 8 findings 197/wk Cap. High
Midscene Source verified npm
B
@midscene/mcp

Deprecated - Use @midscene/web-bridge-mcp, @midscene/android-mcp, or @midscene/ios-mcp

Security & Testing Score 88/100 3 findings 172/wk Cap. High
Stitch Kit Source verified npm
B
@booplex/stitch-kit

Your coding agent designs terrible UI. stitch-kit wires it into Google Stitch MCP and teaches it the whole pipeline — ideation, screen generation, design systems, production components. Claude Code, Codex, OpenCode, Crush, Cursor, VS Code, Gemini CLI.

Developer Tools Score 88/100 2 findings 167/wk Cap. High
Compiler Source verified npm
B
@axint/compiler

Proof and repair for Apple coding agents: validate Swift, run Xcode evidence, repair failures, and generate inspectable Apple-native capabilities.

AI & Agents Score 88/100 11 findings 150/wk Cap. High
Pop Pay Source verified npm
B
pop-pay

The runtime security layer for AI agent commerce. Drop-in CLI + MCP server — blocks hallucinated purchases and keeps card credentials out of agent context. It only takes 0.1% of hallucination to drain 100% of your wallet.

Security & Testing Score 88/100 7 findings 142/wk Cap. High
Cursor Telegram Chat Source verified npm
B
cursor-telegram-chat

Control the Cursor AI agent from a chat app (Telegram, Discord, GitHub) — with image attachments and voice notes transcribed to text. Pluggable transport adapters + a local daemon + MCP tools + hooks.

Developer Tools Score 88/100 6 findings 113/wk Cap. High
Map Traveler Source verified npm
B
@mfukushim/map-traveler-mcp

Virtual traveler library for MCP

Lifestyle & Local Score 88/100 3 findings 111/wk Cap. High