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 →
Discord Source verified npm
B
@tensakulabs/discord-mcp

Discord selfbot MCP server — read & send messages via Claude

Developer Tools Score 85/100 6 findings 16/wk Cap. High
Claude Project Source verified npm
B
claude-project

Project brain for Claude Code — .claude-project v5, event log, registry, dispatch queue, agent orchestration, daemon, MCP memory server, CLI, VS Code integration, research instrumentation, Protocol Documents, typed dispatch, prompt caching

Developer Tools Score 85/100 8 findings 15/wk Cap. High
Proofscan Source verified npm
B
proofscan

MCP Server scanner - eliminate black boxes by capturing JSON-RPC from connection to tools/list

Security & Testing Score 85/100 10 findings 14/wk Cap. High
Codemode Bridge Source verified npm
B
@ruifung/codemode-bridge

MCP bridge that connects to upstream MCP servers and exposes tools via a single codemode tool for orchestration

Developer Tools Score 85/100 8 findings 13/wk Cap. High
Whatnext Ai npm
B
whatnext-ai

What Next — AI-powered continuity engine. Your second brain that always knows what happened and what comes next.

Developer Tools Score 85/100 8 findings 13/wk Cap. High
Claude Persistent Memory npm
B
@alex900530/claude-persistent-memory

Persistent memory system for Claude Code — hybrid BM25 + vector search, LLM-driven structuring, automatic clustering

AI, Memory & Reasoning Score 85/100 8 findings 11/wk Cap. High
Reflect npm
B
reflect-mcp

MCP server for Reflect Notes - connect your notes to Claude Desktop. Just run: npx reflect-mcp

Developer Tools Score 85/100 5 findings 10/wk Cap. High
AWS Source verified npm
B
@antidrift/mcp-aws

AWS connector exposing S3, Lambda, ECS, CloudWatch, SQS, and Cost Explorer via the AWS CLI.

Cloud & DevOps Score 85/100 6 findings 7/wk Cap. High
Ds Toolkit PyPI
B
mcp-ds-toolkit-server

Pure standalone MCP Data Science Server - Complete DS workflows with local SQLite tracking, no external services required

AI & Agents Score 85/100 5 findings Cap. Moderate
Just Domain Remote
B
https://mcp.justdomain.ai/

Search domain availability and pricing, straight from chat — then open a link to register.

Web, Search & Scraping Score 85/100 1 finding Cap. Minimal
Local Mcp Remote
B
https://local-mcp.com/mcp

180 local tools from ChatGPT, Claude.ai & desktop AIs: Mail, iMessage, Teams, files. Local, free.

Communication & Collaboration Score 85/100 18 findings Cap. High
Ms 365 Source verified npm
B
@softeria/ms-365-mcp-server

A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API

AI, Memory & Reasoning Score 84/100 4 findings 47k/wk Cap. Critical
Email Source verified npm
B
@codefuturist/email-mcp

Email MCP server with IMAP and SMTP support.

Productivity & Workflow Score 84/100 6 findings 5.6k/wk Cap. Critical
Memorix Source verified npm
B
memorix

Local-first shared memory layer for AI coding agents across MCP clients, Git history, reasoning context, and project sessions.

AI, Memory & Reasoning Score 84/100 13 findings 1.9k/wk Cap. Critical
Playwright 4 implementations
B
best: mcp-playwright

Forked Playwright Tools for MCP with network changes

Browser Automation Best score 84/100 2 findings 1.4k/wk Cap. Minimal
Mcpfusion Core npm
B
@mcpfusion/core

MVA (Model-View-Agent) framework for the Model Context Protocol. Structured perception packages with Presenters, cognitive guardrails, self-healing errors, action consolidation, and tRPC-style type safety — so AI agents perceive and act on your data det

Security & Testing Score 84/100 14 findings 1.2k/wk Cap. High
Algosuite Vo npm
B
@algosuite/vo-mcp

Virtual Office MCP server — open protocol surface for the VO consensus / ratchet tool family. Stdio transport, cross-vendor MCP client compatible (Claude Code, Claude Desktop, Cursor, Continue).

Learning & Documentation Score 84/100 9 findings 694/wk Cap. High
Protect npm
B
protect-mcp

Fail-closed Cedar policy gate + Ed25519 signed receipts for AI agent tool calls. Denies on any policy error, proves the gate is live with a startup self-test, and turns every decision into a local searchable record you own. The open gate behind Legate by

Security & Testing Score 84/100 22 findings 693/wk Cap. High
Feishu User Plugin npm
B
feishu-user-plugin

All-in-one Feishu MCP server + CLI tool for Claude Code / Codex / Cursor / scripts — 85 tools across 3 auth layers (cookie / app / OAuth). Send as you, read groups, manage docs / bitable / wiki / drive / calendar / tasks / OKR.

Productivity & Workflow Score 84/100 13 findings 369/wk Cap. High
Markitdown Mcp Npx npm
B
markitdown-mcp-npx

NPX wrapper for Microsoft's MarkItDown MCP server - run without Docker. Provides the same file conversion capabilities (PDF, Word, Excel, images, etc.) as the original Docker version but with easier setup and direct file system access.

Other Score 84/100 4 findings 317/wk Cap. High
Cogmemai npm
B
cogmemai-mcp

CogmemAi: Autonomous Cognitive Memory for Any Ai System. 95.10% on LongMemEval (top published score on the field's hardest long-term memory benchmark) and 91% on LoCoMo (above human performance). Autonomous memory capture: your Ai's work is saved even whe

AI, Memory & Reasoning Score 84/100 6 findings 254/wk Cap. High
Text Editor npm
B
mcp-server-text-editor

An open source implementation of the Claude built-in text editor tool

Other Score 84/100 4 findings 170/wk Cap. High
Mind Map npm
B
mind-map-mcp

Mind Map Model Context Protocol server for Claude Code - intelligent project knowledge graph with brain-inspired intelligence

Developer Tools Score 84/100 9 findings 153/wk Cap. High
Brightspace Source verified npm
B
brightspace-mcp

MCP server for D2L Brightspace (multi-auth, opt-in writes, session cache)

Learning & Documentation Score 84/100 5 findings 114/wk Cap. Critical