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 →
Camoufox npm
B
mcp-camoufox

MCP server for stealth browser automation via Camoufox — 79 tools, Chrome DevTools MCP-level power with anti-bot stealth

Browser Automation Score 87/100 2 findings 171/wk Cap. High
Codedev Source verified npm
B
codedev-mcp

Universal code development MCP server — search, analyze, navigate, review any codebase. 29 tools, semantic search, AST parsing, security scanning, dead code detection, complexity heatmaps, DB schema parsing, API discovery, IaC analysis, CI/CD parsing, mon

Developer Tools Score 87/100 15 findings 167/wk Cap. High
Whoop 2 implementations
B
best: whoop-mcp-server

MCP server for the WHOOP Developer Platform API

Analytics & Monitoring Best score 87/100 2 findings 163/wk Cap. High
Claude Recall Source verified npm
B
claude-recall

Persistent memory for Claude Code and Pi with native Skills integration, automatic capture, failure learning, and project scoping

AI, Memory & Reasoning Score 87/100 10 findings 159/wk Cap. High
Yandex Webmaster npm
B
yandex-webmaster-mcp

MCP server for Yandex Webmaster API - site analytics, indexing status, search queries, and SEO diagnostics

Web, Search & Scraping Score 87/100 2 findings 159/wk Cap. High
Selis npm
B
@calx/selis-mcp

MCP server for Selis TMiS — manage PMO entities (actions, risks, issues, projects) from any MCP client

Productivity & Workflow Score 87/100 2 findings 152/wk Cap. High
Alethia npm
B
@vitronai/alethia

MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet

Security & Testing Score 87/100 2 findings 141/wk Cap. High
Claude Code npm
B
@kunihiros/claude-code-mcp

MCP server for Claude Code

Developer Tools Score 87/100 5 findings 132/wk Cap. High
Applescript npm
B
@peakmojo/applescript-mcp

MCP server for executing AppleScript

Other Score 87/100 3 findings 123/wk Cap. High
Mneme Ai npm
B
@mneme-ai/mcp

MCP server that exposes Mneme to Claude Code, Cursor, Continue, and other AI clients

Security & Testing Score 87/100 13 findings 122/wk Cap. High
Spritecook npm
B
spritecook-mcp

SpriteCook MCP Server - Connect your AI agent to SpriteCook for game asset generation, saved presets, import, background cleanup, asset organization, inspection, and animation.

Gaming & Entertainment Score 87/100 2 findings 120/wk Cap. High
Sharplens npm
B
sharplens-mcp

MCP server providing 91 AI-optimized tools for .NET/C# semantic code analysis using Roslyn.

Developer Tools Score 87/100 2 findings 118/wk Cap. High
Advanced Sqlite Memory Bank npm
B
@andrebuzeli/advanced-sqlite-memory-bank

Advanced SQLite Memory Bank MCP v1.10.9 - HIGH PERFORMANCE AI AGENT MEMORY SYSTEM with 9 specialized tools + MCP Resources. REAL DATABASE ONLY - COMPLETELY SILENT NO JSON INTERFERENCE. Hierarchical ID system (T1.0.0, M1.1.0, P1.1.1), 7 status types, batch

Developer Tools Score 87/100 2 findings 116/wk Cap. High
Atlas Pipeline npm
B
atlas-pipeline-mcp

Revolutionary MCP server with 31 AI-powered tools including 6 next-gen tools: Codebase Surgeon, Bug Oracle, Code Whisperer, Tech Debt Quantifier, Semantic Search, Smart Merge Resolver. Works with Cursor, Windsurf, Claude Desktop.

Developer Tools Score 87/100 7 findings 116/wk Cap. High
Openwriter npm
B
openwriter

The open-source writing surface for AI agents. Markdown-native editor with pending change review — your agent writes, you accept or reject.

Productivity & Workflow Score 87/100 13 findings 115/wk Cap. High
When npm
B
@whenlabs/when

The WhenLabs developer toolkit — 6 tools, one install

AI & Agents Score 87/100 4 findings 115/wk Cap. High
Outlook npm
B
outlook-mcp

Comprehensive MCP server for Claude to access Microsoft Outlook and Teams via Microsoft Graph API - including Email, Calendar, Contacts, Tasks, Teams, Chats, and Online Meetings

Developer Tools Score 87/100 2 findings 114/wk Cap. High
Gitea Mcp Tool npm
B
gitea-mcp-tool

Universal MCP Server for Gitea - 通用 MCP 服务器,支持 Claude Desktop、Cline、Continue 等所有符合 MCP 规范的客户端访问 Gitea API

Developer Tools Score 87/100 3 findings 110/wk Cap. High
Vibe Annotations npm
B
vibe-annotations-server

Global MCP server for Vibe Annotations browser extension

Developer Tools Score 87/100 6 findings 107/wk Cap. High
Cardano npm
B
@indigoprotocol/cardano-mcp

Cardano MCP server for handling wallet interactions

Finance & Commerce Score 87/100 0 findings 105/wk Cap. Minimal
Apple Photos Source verified npm
B
apple-photos-mcp

MCP server for Apple Photos - query, search, export, and inspect the macOS Photos library via Claude and other AI assistants, plus opt-in album/metadata write tools (read-only by default)

Web, Search & Scraping Score 87/100 5 findings 103/wk Cap. High
Github Rag npm
B
github-rag-mcp

MCP server for semantic search of GitHub issues/PRs via Cloudflare Worker

AI, Memory & Reasoning Score 87/100 2 findings 103/wk Cap. High
Live Translate 2 implementations
B
best: live-translate-mcp

MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper

API Development Best score 87/100 4 findings 101/wk Cap. High
Plumb npm
B
plumb-mcp

The two-way Figma MCP server: extract designs as compact specs and verify your code with a built-in loop (design → code), OR turn a prompt into a full, on-brand Figma design directed by an AI design director that researches references, extracts a brand, a

Design & Media Score 87/100 2 findings 100/wk Cap. High