- OpenTranscribe MCP @fbossiere/open-transcribe-mcpProvider-independent speech-to-text with normalized transcripts over MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Anytype (self-hosted HTTP) @ohneben/anytype-mcpSelf-hosted Anytype MCP server: the full Anytype API as an always-on Docker + HTTP endpoint.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- YunoHost MCP @imattau/yunohost-mcpNostr-authenticated MCP server for secure YunoHost administration.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Toyota & Lexus @zepgram/toyotaToyota & Lexus vehicles: fuel, range, location, trips, health, climate, charging, commands7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Umami @asif2bd/umami-mcpQuery Umami Analytics v3 — stats, funnels, retention, attribution, UTM. Read-only by default.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Inferrail @domondi1/inferrailLocal, payload-free AI cost visibility for agents. Query spend by model, route, or tagged work.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Itsoc @ankit512/itsoc-mcpRead-only MCP server over a local log-analysis backend; a client that computes no verdicts.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- hybridlog @imgrund/hybridlogReads your own Garmin mirror: readiness, training load, muscle freshness, and read-only SQL.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Gatewerk @gatewerk/mcpThe open-source review layer for AI agents. Work done for humans is decided by humans.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Health Hub MCP @naymevg/health-mcpSelf-hosted MCP server for Android Health Connect — 34 metrics, daily rollups, dedup, 5 LLM tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Agentic Wallet Guardian V3 @rudimentall1/agentic-wallet-guardian-v3Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- TrueNAS SCALE @cedricziel/truenas-mcpInspect and manage TrueNAS SCALE storage, shares, apps and system state with your own API key3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Cortex @vblackjack/cortexLocal multi-client RAG server over the Model Context Protocol.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- MCP VS Code @mario-andreschak/mcp-vscodeA self-hosted VS Code workbench embedded as an interactive MCP App.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Oe @enthrium/oe-mcpConnect any AI coding app to enterprise data sources. One binary, one JSON config.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Mcpcut @musyta-labs/mcpcutOrccut: a real timeline video editor for AI agents - journaled edits, FFmpeg/MLT rendering7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Linkwarden MCP @flumpiey/linkwarden-mcpRead-first Linkwarden bookmarks MCP with opt-in write, delete, and collection tools.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Oe @openenterprise-info/oe-mcpConnect Claude Code, Cursor & Windsurf to 2,600+ enterprise data sources with one binary.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Manager.io MCP @flumpiey/manager-mcpMCP server for Manager.io bookkeeping: read-first with opt-in scoped task and write tools3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Gaggiuino @ljcl/gaggiuino-mcpRemote MCP server for your Gaggiuino espresso machine's shots and profiles3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- chatmux @echoedinvoker/chatmuxLocal-first MCP server for your own LINE and Telegram chats. Data stays on your machine.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Laguarde @futur-panda/laguardeSelf-hostable policy control plane for AI coding agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- n8n MCP Community @drzamarian/n8n-mcp-communityA security-focused MCP server for self-hosted n8n Community Edition.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Yahoo! Shopping MCP @ymuichiro/yahoo-shopping-mcpRead-only Yahoo! Shopping product search via the Yahoo! Shopping Item Search API v3.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
