- Grantd @rafavecchi/grantdGrantd MCP server: let your AI agent act on a user's behalf across third-party APIs via OAuth.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Image Generation MCP Server @pvliesdonk/image-generation-mcpMCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Kalshi MCP Server @joinquantish/kalshiSelf-hosted MCP server for Kalshi prediction market trading via DFlow on Solana6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- Tronbyt @jonfishr/tronbyt-mcpControl Tidbyt/Tronbyt LED displays: push text, images, and apps; brightness and night mode.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- GoodSender @good-sender/goodsender-mcpFree consent-based emailing, blog publishing, and interactive email template design tools10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- Groundhog @dmytrome/groundhog-mcpSearch, read and research the web, with hidden text stripped by default and sources hashed7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- KIP MCP Server @dillan/kip-mcp-serverReads a boat's Signal K data and helps an AI assistant design and install KIP dashboards.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- memex @ayushagrawal288/memexPersistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- mcp-egrul @atomno-mcp/mcp-egrulEGRUL/EGRIP company registry lookup for Russian legal entities and entrepreneurs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Nr @texan-nxtassist/nr-mcpMCP server for Node-RED — safe deploy, optimistic locking, smart search, 13 tools4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Nandi Proxmox @nandi-services/nandi-proxmox-mcpMCP server for Proxmox VE management (VM, LXC, nodes)6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Switchboard @jemplayer82/mcp-switchboardSelf-hosted MCP message bus: agents DM each other, broadcast to channels, and track presence.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Tidebase @blueprintlabio/tidebaseInspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Atlas @atlasdevhq/atlasAtlas is a YAML-defined semantic layer for analytics — authored by humans, consumed by AI agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- SuiteCRM @anirudhx7/suitecrm-mcpOpen-source MCP gateway for SuiteCRM - 24 CRM tools, OAuth2/OIDC auth, multi-entity, observability.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Plexus @pcas-io/plexusTyped on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.1 GitHub stars.
- AON @leo007-htun/aonSelf-hosted, uncensored AI agent: ask it tasks, search its long-term memory and your documents.Not assessed yet.Runs on your machine, installed from PyPI.
- Synology Chat @louis-lastella/synology-chat-mcpRead channels and posts, find users, send messages and files on any Synology Chat server.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Mailroom @darrylmosher/mailroomSelf-hosted gateway between your iCloud mailbox and your AI assistant, with safety built in3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Qdrant RBAC @fidonis/qdrant-mcp-rbacRole-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Futureweb Intervals MCP @futureweb/intervals-mcp-serverSelf-hosted Intervals.icu MCP server: training analytics, Garmin data, wellness, workout planning3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Spawner @flosk6/spawnerPreview environments on your self-hosted Spawner server: a copy of your app for each git branch3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Maplith Bridge @maplith/bridgeShare a folder of data files read-only over MCP, and fill it from PostgreSQL under a read-only role.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- LingJing @genesis-plan/lingjingLingJing classroom MCP: human teaches, AI student questions; returns blindspots & summary.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
