- New Relic MCP Server @meet-bhalodiya/newrelic-mcpSecure, self-hosted New Relic observability and administration tools for MCP clients4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- BrainLLM @miisodev/brainllmSelf-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Bamboo MCP Server @hmdmph/bamboo-mcpRead-only MCP server for self-hosted Atlassian Bamboo CI/CD4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- tollbooth @chrzanowy/agent-tollboothStateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Longhorn @rafaelgaspar/longhorn-mcpMCP server for the Longhorn distributed storage manager API, with a --read-only mode.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- tube-bridge @thewhitewater/tube-bridgeYouTube MCP server for search, transcripts, frames, comments, channels, and local semantic corpora.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Attestari @attestari/attestariAuditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Taskswarm @rudrendupaul/taskswarmWraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- WorkspaceGuard @rudrendupaul/workspaceguardWraps the WorkspaceGuard CLI as a single generic MCP tool for workspace usage checks.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- tubekit @santiriera626/tubekit-mcpCompliance-aware MCP server for YouTube publishing, analytics and creator insights.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Telegram Managed Bot Factory @laser54/bot-factoryProvision owner-confirmed isolated Telegram Managed Bot instances.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- garnet-mcp @tarazou9/garnet-mcpRAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- Ocultar PII @edu963/ocultar-piiZero-egress PII redaction for Claude. Runs locally — no data leaves your infrastructure.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- HYTHE @hythe/hytheHYTHE — coordination bus + shared truth for AI agent fleets — self-hosted MCP server + stdio bridge.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- mailindex-mcp @alexanderkrauck/mailindex-mcpSearch, move, mark, delete and draft your real mail over a self-hosted index.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- X402 Accept @cryptoapis-io/mcp-x402-acceptSelf-hosted MCP proxy that puts an x402 paywall in front of an existing MCP server6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Rails @jaimenbell/rails-mcpDefault-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Fetchmux @krutftw/fetchmuxSelf-hosted retrieval router for AI agents: budgets, provider routing, route receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PixLint @amitsingh-24/pixlintLint, curate & prepare computer-vision datasets from your AI assistant — MCP server, 67 tools4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Mailwarden @csitte/mailwardenGmail MCP server for email triage: search, labels, archive, trash, unsubscribe, snooze.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Panella @panellatech/panellaGoverned, self-hosted memory for AI agents: writes queue until a named person approves.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Awesome Coolify @clezcoding/awesome-coolifyCoolify 4.1.x MCP server — deploy, diagnose, and manage apps, services, and databases5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Hiberden @agaveis/hiberden-mcpRead and verify your local media archive's 3-2-1 coverage across tape, disk, NAS, and cloud.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Zephyr Scale @vilaabo/zephyr-scale-mcpZephyr Scale on self-hosted Jira Server/DC: test cases, cycles, executions, plans and attachments4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
