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 →
Telegram Mcp Windows Amd64 npm
B
@chaindead/telegram-mcp_windows_amd64

Telegram MCP server with API integration for accessing user data, managing dialogs (chats, channels, groups), retrieving messages, and handling read status.

Communication & Collaboration Score 87/100 0 findings 348/wk Cap. Minimal
Computer Use npm
B
computer-use-mcp

💻 MCP server for Claude to control your computer

Browser Automation Score 87/100 3 findings 327/wk Cap. High
Last9 Source verified npm
B
@last9/mcp-server

Last9 MCP Server - Model Context Protocol server implementation for Last9

Analytics & Monitoring Score 87/100 4 findings 327/wk Cap. High
Telegram Mcp Linux Arm64 npm
B
@chaindead/telegram-mcp_linux_arm64

Telegram MCP server with API integration for accessing user data, managing dialogs (chats, channels, groups), retrieving messages, and handling read status.

Communication & Collaboration Score 87/100 0 findings 323/wk Cap. Minimal
Telegram Mcp Darwin Amd64 npm
B
@chaindead/telegram-mcp_darwin_amd64

Telegram MCP server with API integration for accessing user data, managing dialogs (chats, channels, groups), retrieving messages, and handling read status.

Communication & Collaboration Score 87/100 0 findings 322/wk Cap. Minimal
Telegram Mcp Windows Arm64 npm
B
@chaindead/telegram-mcp_windows_arm64

Telegram MCP server with API integration for accessing user data, managing dialogs (chats, channels, groups), retrieving messages, and handling read status.

Communication & Collaboration Score 87/100 0 findings 321/wk Cap. Minimal
Nowaikit npm
B
nowaikit

The Most Comprehensive ServiceNow AI Toolkit — 450+ MCP tools + 26 AI capabilities (scan, review, build, ops, docs) + direct BYOK mode. Integrates with Claude, ChatGPT, Gemini, Cursor, GitHub Copilot and any LLM.

Other Score 87/100 14 findings 308/wk Cap. High
Ellmos Codecommander npm
B
ellmos-codecommander-mcp

A developer-focused MCP server providing 21 tools for code analysis, JSON repair, encoding fix, import organization, Python runtime import diagnostics, structural Python editing, indentation checks, code generation, format conversion, diff, and regex test

Developer Tools Score 87/100 2 findings 289/wk Cap. High
Ddc Ci Control Bridge npm
B
ddc-ci-control-bridge

Multi-protocol bridge for DDC/CI monitor control with MCP and MQTT support

Developer Tools Score 87/100 0 findings 286/wk Cap. Minimal
Mailbridge npm
B
mailbridge-mcp

Connect your AI assistant to email — read, search, send, and organise via IMAP/SMTP

Web, Search & Scraping Score 87/100 5 findings 271/wk Cap. High
Metamcp npm
B
@mentu/metamcp

A meta-MCP server that collapses N child MCP servers into 4 tools. Intent routing, lazy spawning, connection pooling, semantic search, and sandboxed code execution.

Productivity & Workflow Score 87/100 5 findings 267/wk Cap. High
Speclock npm
B
speclock

Stop AI from breaking code you told it not to touch. Enforces .cursorrules, CLAUDE.md, and AGENTS.md — not just suggests. Zero-config: npx speclock protect reads your existing AI rule files, extracts constraints, installs pre-commit hooks, and makes your

Security & Testing Score 87/100 5 findings 263/wk Cap. High
Tmux npm
B
tmux-mcp

MCP Server for interfacing with tmux sessions

Other Score 87/100 4 findings 256/wk Cap. High
Ori Memory npm
B
ori-memory

Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.

AI, Memory & Reasoning Score 87/100 9 findings 247/wk Cap. High
Md Redline npm
B
md-redline

Inline review comments for markdown specs. Built-in MCP server hands feedback directly to your AI agent.

Developer Tools Score 87/100 4 findings 237/wk Cap. High
Unicli Source verified npm
B
@zenalexa/unicli

Open Agent-Computer Interface runtime for discovering, selecting, governing, acting through, observing, and repairing operations across real software.

Developer Tools Score 87/100 18 findings 236/wk Cap. High
Youtube Shorts Agent npm
B
youtube-shorts-agent

Agent-first YouTube Shorts upload CLI and MCP server with dry-run uploads, OAuth readiness and synthetic-media metadata.

AI & Agents Score 87/100 3 findings 229/wk Cap. High
Real Chrome npm
B
mcp-real-chrome

MCP server that gives AI access to your real Chrome tabs via a bridge extension

Developer Tools Score 87/100 0 findings 224/wk Cap. Minimal
Bnb Chain npm
B
@bnb-chain/mcp

A MCP server for BNB Chain that supports BSC, opBNB, Greenfield, and other popular EVM-compatible networks.

Other Score 87/100 0 findings 219/wk Cap. Minimal
Oura npm
B
@daveremy/oura-mcp

Oura Ring MCP server and CLI — sleep, readiness, activity, HR, stress, SpO2, workouts, and more

Lifestyle & Local Score 87/100 3 findings 208/wk Cap. High
Sap Adt npm
B
sap-adt-mcp

MCP server giving Claude live access to SAP systems via ADT (ABAP Development Tools) REST. Read source, search, run syntax checks, and edit ABAP objects from any MCP-compatible client.

AI & Agents Score 87/100 2 findings 205/wk Cap. High
Odyssey365 npm
B
@odyssey365/mcp-server

Odyssey MCP Server — MCP 호환 AI 클라이언트에서 Odyssey의 할일/메모/타임라인을 관리

Productivity & Workflow Score 87/100 5 findings 197/wk Cap. High
Perplexity Comet npm
B
perplexity-comet-mcp

Production-grade MCP server bridging Claude Code with Perplexity Comet browser - Windows support, tab management, smart completion detection

Learning & Documentation Score 87/100 2 findings 177/wk Cap. High
Par5 npm
B
par5-mcp

MCP server for parallel list operations - run shell commands and AI agents across lists in parallel

AI & Agents Score 87/100 0 findings 172/wk Cap. Minimal