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.
MCP server for tmux, powered by libtmux
MCP server for the Lightbulb Partners Agents platform — Claude Code, Codex, and Cursor integration
Safety-first MCP server exposing Lighter perpetual-DEX trading to AI agents (Cursor, Claude, Codex, Claude Desktop, OpenClaw).
Part of Lightning Enable — infrastructure for agent commerce over Lightning. MCP server for L402 Lightning payments, API discovery, and agent commerce.
The whole local AI stack in one executable: run and manage local AI models across every GPU you have, and search your files, code, and the web pages you crawl, with answers that cite the source. Per-project libraries, semantic and hybrid search, vision OCR, an auto-built wiki, CLI, TUI, MCP server, REST API, and Python library. No model server, no database server, no containers. Works with your own Ollama or LM Studio models too.
MCP server for read-only Linux system administration, diagnostics, and troubleshooting
MCP server for querying Linux kernel docs, code, and APIs.
The definitive Model Context Protocol bridge for Ableton Live
AI-powered C/C++ debugger via LLDB and Model Context Protocol. 40 debugging tools for Claude Code and Claude Desktop.
Local-first AI memory cartridge: persistent, cross-session memory for Claude and any LLM via MCP
Multi-LLM router MCP server — smart complexity routing, budget-aware model selection, 20+ providers (Claude, OpenAI, Gemini, Ollama, etc.)
MCP (Model context protocol) server with LLMling backend
Delegate mechanical text tasks to a local OpenAI-compatible LLM endpoint to conserve Claude subscription quota.
MCP server with FAISS local vector database for RAG
100% local RAG for Obsidian, Zotero, and Claude Code — LightRAG + Ollama + MCP
MCP server for databases, spreadsheets, structured files, and directed graphs.
Local Ollama-backed MCP server — 45 tools, smart buffer, execution filters, persistent scratchpad, settings GUI
Hierarchical markdown memory palace for AI agents — MCP server, skills, and audit tools
MCP Server for geospatial operations - geocoding, routing, spatial analysis
Celeste map editor for AI agents — MCP server for reading, editing, previewing, and procedurally generating .bin map files
Intelligent log analysis for LLMs - extract patterns, redact secrets, compress 50%+
Pluggable, multi-store memory for any AI system — episodic, semantic, temporal-graph and dialectic user memory in one library.
A tool to help agents read and query long documents.
Persistent local memory for Claude Code. Total recall from your session files — no API calls, no summaries, no AI deciding what matters.