- Cortex @tootie/cortexSyslog receiver and MCP server for homelab log intelligence.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Syslog MCP @tootie/syslog-mcpSyslog receiver and MCP server for homelab log intelligence.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- Flash @flashmemorize/flashSpaced-repetition flashcards your AI writes, quizzes you on by voice, and schedules with FSRS.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- qsearch @theyahia/qsearchMulti-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- OpenCode MCP Bridge @manuotel/opencode-mcp-bridgeCoordinate and verify OpenCode workers over MCP Streamable HTTP.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- WPWriter — WordPress AI Content & SEO @wpwriter/wordpressWordPress MCP server: generate SEO posts, AI images, autoblog & WooCommerce on your self-hosted site11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 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.
- 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.
- 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.
- Kumbuka @kumbuka/kumbuka-serverGoverned, auditable knowledge your team curates for its AI assistants, self-hostable4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Ownership Provenance Protocol @bg4ff8mtdn-dotcom/ownership-provenance-protocolMCP protocol requiring task acceptance and provenance tags. Self-hosted only - see README.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Munnin — an agent identity server @alvseek/munninAgent identity and memory over MCP — a persistent self plus the procedures for tending it.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Giljo HQ @giljo/hqContext engineering for AI coding agents: product context, project missions, and 360 memory.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- PSE Edge @phdwight/pse-edge-mcpPhilippine Stock Exchange data via PSE Edge: EOD quotes, price history, disclosures, financials.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- seenpaid @seenpaid/seenpaidAgentic social media scheduler: 21 platforms, 50 MCP tools, and which posts made money via Stripe.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Bureau (about) @getbureau/aboutAbout Bureau, the self-hosted office for AI agents: overview, FAQ search, roadmap, install.2% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent DVR @ispyconnect/agentdvrAsk your security cameras anything and set up alert rules in a sentence. Built into Agent DVR.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Runtime @formatho/runtimeSelf-hosted MCP server: 26 deterministic dev, security, and EVM tools.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MinIO Postgres Redis Stack Generator @getvda/minio-postgres-redis-stack-generatorMinIO + Postgres + Redis Stack Generator8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Zoxron MCP @zoxron/mcpYour AI agent deploys, migrates & upgrades self-hosted Odoo ERP on a server you own.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Localtonet MCP @localtonet/mcpSecure tunneling, reverse proxy and remote access for local applications.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Fractera @fractera/deployZero-Ops deploy of a private AI workspace to your own VPS — from your AI chat. Free and open-source.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
