- Provena Agent Memory @admiralpunk/provena-memorySelf-hosted MCP memory for AI agents: persistent context with evidence-backed claims.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Fanout @labstack/fanoutInvestigate OpenTelemetry traces, metrics, and logs, and manage personal dashboards.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.6 GitHub stars.
- Mnema — Shared Brain for You and Your AI Agents @theboringpeople/mnemaSelf-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.6 GitHub stars.
- SSH MCP Server @hypnosis/ssh-mcp-serverModern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- RE-call MCP Memory Server @giulioder/re-callAgent memory on your own Postgres that flags superseded facts and abstains instead of guessing.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Précis Finance MCP @precis-finance/precis-finance-mcpPublic read-only Précis Finance MCP demo with synthetic data; no account or credentials required.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- Artifacts @kuyazee/artifactsSelf-hosted artifact publishing: POST HTML/JSX/Markdown/zip, get an unguessable URL on your domain5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.6 GitHub stars.
- mwe-mcp — Memory Wiki Engine @fr4nz82/mwe-mcpSelf-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.6 GitHub stars.
- TIDAL @ibeal/tidal-mcpMCP server for TIDAL - search tracks, manage playlists, and get personalized recommendations5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.6 GitHub stars.
- Forkflux @forkflux/forkflux-mcpSelf-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- clawops @dfridkin/clawopsDeploy self-hosted OpenClaw to AWS, GCP, Azure or a local VM — a CLI and an MCP server in one.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- pfSense @antonio-mello-ai/mcp-pfsenseManage pfSense firewalls through AI assistants — rules, DHCP, DNS, and more5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Strata @agenerationforwordz-tech/strataSelf-hosted AI memory server. Persistent memory on your hardware, not the cloud.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Oriel @paradoxinfinite/orielSafety-gated AI control of Docker and Colima: containers, images, volumes, networks, Compose.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.6 GitHub stars.
- Telegram Archive @geiserx/telegram-archive-mcpMCP server for Telegram Archive — search messages, browse chats, and access history7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- MCP Gateway @panossalt/mcp-gatewayMulti-tenant MCP platform with OAuth 2.1, Entra SSO, RBAC and audit logging.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- ToolMesh @dunkelcloud/toolmeshSelf-hosted MCP gateway. Turn any REST API into MCP tools via YAML (DADL). Authz, audit, policies.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.6 GitHub stars.
- trello-mcp @enthouan/trello-mcpIndependent, community-maintained Trello MCP server. Not an official Trello or Atlassian product.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.5 GitHub stars.
- UNITARES @cirwel/unitaresAccountability infrastructure for long-running AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.5 GitHub stars.
- Casefile @azimov777/casefileSelf-hosted MCP server: a case file for every task, shared across sessions, agents and people.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.5 GitHub stars.
- Kybase @kyrzin/kybaseSelf-hosted Markdown memory for AI agents: notes you can read and edit, with hybrid search.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- million @kelows/millionOperate a self-hosted Solana whale tracker and copy-trading deck: positions, rules, token checks.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Agentic SSH @sandbanks/agentic-sshHigh-performance (Rust), token-efficient, and asynchronous SSH orchestrations for AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.5 GitHub stars.
- Perfex CRM @themesic/perfex-crmRead and write a self-hosted Perfex CRM from an AI agent: 148 permission-filtered tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.5 GitHub stars.
