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 →
Ai Verify npm
C
@validpilot/ai-verify-mcp

AI 编程验证平台。让 AI 代码生成结果可验证、可信赖。MCP 协议原生支持,证据驱动。

Browser Automation Score 71/100 16 findings 29/wk Cap. High
Coding Agents npm
C
@kadreio/mcp-coding-agents

MCP server with multiple AI coding agents for enhanced development workflows

Developer Tools Score 71/100 11 findings 23/wk Cap. High
Oioxo npm
C
oioxo-mcp

OIOXO — cut your AI bill by up to ~90%: it feeds Claude Code, Copilot, Cursor and any MCP agent only the relevant slice of your codebase instead of whole files. Also a private terminal coding agent (`oioxo code`, on-device with --local or any key). Runs o

AI & Agents Score 71/100 7 findings 15/wk Cap. High
Puppeteer Linux npm
C
mcp-puppeteer-linux

MCP server for browser automation using Puppeteer with X11/Wayland support

Browser Automation Score 71/100 8 findings 15/wk Cap. High
Electric Cherry npm
C
electric-cherry

Electron debugging MCP server for renderer (CDP) and main process (V8 Inspector)

Browser Automation Score 71/100 6 findings 14/wk Cap. High
Algochains PyPI
C
algochains-mcp-server

AlgoChains MCP Server — 533 tools for live algo trading: Tradovate/Alpaca/OANDA, Databento/Polygon data, Onyx RAG, Graphiti KG, AlphaLoop, HMM regimes, autonomous marketplace pipeline, Kalshi, physical-world event intelligence, real data only.

Finance & Commerce Score 71/100 20 findings Cap. High
Memory Service PyPI
C
mcp-memory-service

Semantic memory layer for AI applications. REST API + MCP transport + knowledge graph + autonomous consolidation. Works with 14+ AI clients. Self-host, zero cloud cost.

Developer Tools Score 71/100 24 findings Cap. High
Mcp Remote
C
https://bigtableadmin.googleapis.com/mcp

Interact with your Google Bigtable resources using natural language commands.

Data Science & ML Score 70/100 4 findings Cap. Moderate
Documcp Source verified npm
D
documcp

Intelligent MCP server for GitHub Pages documentation deployment

AI, Memory & Reasoning Score 69/100 20 findings 31/wk Cap. High
Figma Console 4 implementations
D
best: @mp3wizard/figma-console-mcp

The most comprehensive MCP server for Figma — design tokens, variables, components, write tools, version history diff, accessibility audits, FigJam, Slides, and more. Local (WebSocket Desktop Bridge plugin) and Cloudflare Workers (paired + remote) modes.

Design & Media Best score 67/100 7 findings 172/wk Cap. Critical
Photon npm
D
@portel/photon

Build MCP servers, CLI tools, and web dashboards for AI agents from a single TypeScript file.

Developer Tools Score 67/100 20 findings 120/wk Cap. High
Ira Researcher npm
D
ira-researcher

The most powerful browser automation MCP server — 40 tools, ghost effects, stealth mode, DevTools access. Powered by Neural Nexus Tech (https://neuralnexustech.com/)

Browser Automation Score 67/100 5 findings 17/wk Cap. Critical
Depwire Cli npm
D
depwire-cli

Dependency graph + 23 MCP tools for AI coding assistants. Impact analysis, health scoring, security scanner, agent coordination.

AI & Agents Score 64/100 9 findings 1.8k/wk Cap. Critical
Screenhand npm
D
screenhand

Give AI eyes and hands on your desktop. ScreenHand is an open-source MCP server that lets Claude and other AI agents see your screen, click buttons, type text, and control any app on macOS and Windows.

Browser Automation Score 63/100 18 findings 33/wk Cap. Critical
Shellward npm
D
shellward

AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.

AI & Agents Score 60/100 18 findings 437/wk Cap. High
Pyddock PyPI
D
pyddock

MCP server that gives AI agents pre-approved Python, shell, and file I/O tools with declarative policy controls

Developer Tools Score 60/100 20 findings Cap. High
Infomaniak Mcp Agent npm
F
infomaniak-mcp-agent

Full unofficial agentic Infomaniak MCP server — guided automation of web hosting, mail, kDrive, domains and DNS

AI & Agents Score 56/100 2 findings 178/wk Cap. Critical
Zeph To npm
F
@zeph-to/mcp-server

Zeph MCP server — AI agent notifications, prompts, and input via MCP protocol

Developer Tools Score 55/100 3 findings 45/wk Cap. High
Banking Intelligence Remote
F
https://mcp.ohmyfin.ai/mcp

Cross-border payment & banking intelligence for AI agents: SWIFT/BIC, IBAN, sanctions, FX, tracking.

Finance & Commerce Score 53/100 2 findings Cap. Minimal
Demand Discovery AI Remote
F
https://mcp.demanddiscovery.ai/api/mcp

Sales-agent MCP for Demand Discovery AI. Validate startup ideas with behavioral signals.

Business & CRM Score 53/100 2 findings Cap. Minimal
Atom — Premium Domains Remote
F
https://mcp.atom.com/mcp

Search, value, screen, and buy premium brandable domains from Atom's curated marketplace.

Web, Search & Scraping Score 50/100 2 findings Cap. Moderate
Rate-My-Agent Remote
F
https://mcp.rate-my-agent.com/mcp

Get matched with a top-rated, review-verified real estate agent in the US or Canada.

AI & Agents Score 47/100 3 findings Cap. Moderate
Alexandriashai Mcp Guardian npm
F
@iflow-mcp/alexandriashai-mcp-guardian

MCP security scanner - detect prompt injection in tool descriptions

Security & Testing Score 46/100 12 findings 11/wk Cap. Moderate