- Context @alex-feel/mcp-context-serverAn MCP server that provides persistent multimodal context storage for LLM agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Artel @nicolasprimeau/artelSelf-hosted shared-memory & coordination mesh for AI agent fleets. You host it; agents connect.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.9 GitHub stars.
- Paperless-ngx @cubinet-code/paperless-ngx-mcpFull Paperless-ngx API for AI assistants: search, tag, edit and upload documents, workflows and more3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- ssh-mcp @gelse/ssh-mcpMCP gateway for controlled SSH access with per-client auth, command policies, and audit logging.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- killBottleneck @killbottleneck/killbottleneckGoal and process maps for humans and AI agents on your own server.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- TinyContext @tinysuitehq/tinycontextToken-light local memory with SQLite hybrid retrieval for MCP agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- Unified AI System MCP Gateway @happy520ai/unified-ai-systemSelf-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- Pi-hole MCP Server @hexamatic/pihole-mcpManage Pi-hole v6: DNS blocking, domains, clients, query analysis, DHCP, and multi-instance sync.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- Kortexio Memory @kortexio/memoryHosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.
- Docker MCP Server @l337-org/docker-mcp-serverManage Docker (containers, images, Compose, Swarm, registries) via the Docker SDK and CLI.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Thask @kimgh06/thaskDependency-graph MCP server. Tells Claude/Cursor what breaks if you change X. Provenance guards.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Pihole @aplaceforallmystuff/mcp-piholePi-hole v6 MCP server - manage DNS blocking, stats, whitelists/blacklists4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Recall @recallworks/recallOpen-source MCP memory server. Persistent, searchable, tiered memory across sessions.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Personal Finance @josuem1109/personal-finance-mcpSelf-hosted, read-only MCP server that connects your banks and investments via Plaid.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- Docker MCP Server @gavinlucas/docker-mcp-serverManage Docker (containers, images, Compose, Swarm, registries) via the Docker SDK and CLI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Dakera @dakera-ai/dakera-mcpAgent memory engine — 102 MCP tools, self-hosted, single Rust binary5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- Open Brain @bobby-cell-commits/open-brainGraph-structured MCP memory server. 37.2% LongMemEval. Auto dedup, themes, decay, synthesis.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.
- Fluxmail @fluxmailai/fluxmailRead, search, draft, send, and organize email through Gmail, Outlook, and IMAP/SMTP mailboxes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- OT AIops @aiops-tools/ot-aiopsGoverned OT tap (57 tools): OPC-UA/Modbus/S7/MC/MTConnect/MQTT/EtherNet-IP/EtherCAT.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- Revenueos @unempyd/revenueosSelf-hosted revenue department: find opportunities, execute approved work, measure results.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- Ozon @deviceingineering/ozon-mcp-serverOzon Seller & Performance API, 156 tools; responses trimmed 476k to 64k tokens.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- GCTRL @gctrl-tech/gctrlGoverned graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Agent Memory OS @yamantaka520/agent-memory-osLocal-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- Myco Brain @thegoodguysla/myco-brainSelf-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
