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.
Graph-based MCP memory server for AI coding agents with intelligent relationship tracking and multi-backend support
Mendicant Bias — Ambient intelligence harness for Claude Code with integrated Aletheia verification
Meridian — Local-first AI compliance scanner. DPDPA 2023 · RBI FREE-AI · SEBI AI/ML · EU AI Act. Works with any LLM provider. AST-level code analysis across Python, TypeScript, Go, Java.
A production-grade, cross-platform MCP Server for MetaTrader 5
Unofficial Metasploit MCP Server (not affiliated with or endorsed by Rapid7) - provides Metasploit Framework functionality via the Model Context Protocol. A fork of GH05TCREW/MetasploitMCP.
Metatool MCP Server
An MCP server that generates professional diagrams using the Python diagrams package DSL, with first-class Azure support
Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest
A Model Context Protocol (MCP) server for MigratorXpress, enabling database migration between heterogeneous database systems.
FastMCP server for MikroTik RouterOS management
Unified AI agent framework: one interface for 9 LLM providers (Qwen, Kimi, GLM, DeepSeek, MiniMax, Doubao, ChatGPT, Gemini, Claude) with tools, MCP, sub-agents, skills, RAG knowledge base, scheduler, multi-channel IM gateway (WeChat/Feishu/Telegram) and multi-user serving
MindSync MCP server — local-first multi-agent memory sync and focus conflict detection
MindSync AI — unified MCP server for multi-agent memory, event bus, and CLI agent dispatch
A minimal, stateless, and lightweight framework for building remote MCP servers.
MCP knowledge layer for MiniStack — plug into any IDE AI (Claude Desktop, Cursor, Continue, Windsurf, Cline).
Mijia smart device MCP server, providing device discovery, property read/write, action invoke and other functions
Outcome-conformant synthetic data: realistic multi-table test data that hits the revenue curves, rates, and aggregates you declare, exactly. From a sentence, YAML, or your database. No ML model, no real data. MCP server for AI agents.
Stable since v1.0.0 — MCP server + cross-host agent skill (Claude Code / Codex / OpenClaw / Hermes) for QA testing across pytest / Jest / Cypress / Go / Maestro / Schemathesis / Newman, plus v1.1 Edge AI Runner (RTSP + YOLO). 22 frozen tools, bilingual EN/zh-TW QA knowledge, AI Visual Challenge Solver (reCAPTCHA / hCaptcha), OWASP API Top 10 (2023) scanner, universal qa_plan + verify bookend across 5 core tools (AI 測試大師)
MCP server bridging specs (Linear / JIRA / GitHub Issues / Notion / Markdown / Figma) to tests, with bidirectional traceability and a spec-quality coach (AI 規格大師)
MCP server for MkDocs documentation with intelligent search and retrieval capabilities
MCP server that provides different tools for MLE
MCP server for common MLOps workflows
MCP server bridging Codex to local MLX LM (and any OpenAI-compatible backend)
Local-first semantic memory for AI agents — MLX (Apple Silicon) or CPU sentence-transformers (Linux/Ubuntu) embeddings + sqlite-vec, MCP server. No cloud, no API keys.