- SCF @scfcontrolsplatform/mcp-server-scfMCP server for the SCF Controls Platform — 187 tools for controls, evidence, risk, and TPRM.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Mockups Gallery @kgnatx/mockups-gallerySelf-hosted gallery for AI-generated mockups. MCP interface; token-efficient curl uploads.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- Nginx Proxy Manager @euisuh/nginx-proxy-manager-mcpManage Nginx Proxy Manager hosts, certificates, streams and access lists with dry-run previews.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Workstream @ahmad-codex/workstream-mcpShared task ledger for AI agents and humans: atomic claims, state machine, GitHub and Slack sync5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Cue @murtazox04/cueNotify people through Cue: preferences, attention budgets, quiet hours and approval apply.Not assessed yet.Runs on your machine, installed from PyPI.1 GitHub stars.
- rustunifimcp @mechubsec/rustunifimcpUniFi Network MCP server: scoped tools, audited two-person change control. Rust.Not assessed yet.Runs on your machine, installed from Docker.1 GitHub stars.
- DROP @julesnsenda/dropSelf-hosted PaaS: deploy apps from files or git, read logs, check status, roll back.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- PremAgentic @premagentic/premagenticOn-premises knowledge retrieval, with the rules you set enforced before anything is retrieved.Not assessed yet.Runs on your machine, installed from Docker.1 GitHub stars.
- mcpcut @rostislavmatov/mcpcutJournals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- MedXpert 图书馆连接器（通用版） @zhaoxinghua09-cell/medxpert-library-connectorLocal RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.Not assessed yet.Runs on your machine, installed from a package registry.1 GitHub stars.
- YaCy peer-to-peer search @pad01g/yacy-searchWeb search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service.Not assessed yet.Runs on your machine, installed from Docker.1 GitHub stars.
- Nextcloud Organizer @vando-sketch/nextcloud-organizer-mcpManage Nextcloud tasks, calendar events and notes from Claude over CalDAV and the Notes API.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Tanpin @willykeenan/tanpinItem-by-item inventory that reorders itself: per-SKU forecasts, purchase orders and ETAs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Wakeonlan @cyanheads/wakeonlan-mcp-serverWake LAN machines with Wake-on-LAN magic packets from host profiles, then confirm they came up.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Nacre @nacre/nacreSelf-hosted permission-aware context layer. Search returns only what the caller may read.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Flyto2 Runtime @flytohub/flyto-runtimeSelf-hosted MCP runtime for ChatGPT to edit files, run commands, and test local projects.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- KVM/libvirt VMs and backups (Fedora) @amineutron/fedora-agentsManage local KVM/libvirt VMs and Timeshift/Borg backups on Fedora: start, stop, clone, snapshot.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- HydraDNS @hydradns/hydra-mcpManage a self-hosted DNS firewall: block domains, create policies, read query logs and metrics.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- SearXNG MCP Server @bumbarasch/searxng-mcp-serverSelf-hosted SearXNG metasearch for MCP clients: web, image, news, video, music and page fetch.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ActiveCampaign @ohneben/activecampaign-mcpActiveCampaign API: ~325 endpoints (v3, SMS, WhatsApp, Segments) as safety-categorized MCP tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Engraphy @devon-clarkk/engraphySelf-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- mailmcp @mailmcp-ai/mailmcpYour mailboxes in ChatGPT and Claude: Gmail, iCloud, Fastmail, any IMAP. Passwords stay yours.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Super Log @super-log/super-logQuery your local super-log bench from an AI agent - read-only log tools over the hub.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- LoomaScale Ads @loomascale/adsRun Google Ads and Meta Ads from ChatGPT or Claude: audit wasted spend, create and manage campaigns.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
