- nomArmy @rayson-tech/nomarmySandboxed coding workers, verified: tests rerun fresh and must fail with the change reverted.Not assessed yet.Runs on your machine, installed from npm.4 GitHub stars.
- Sabline @gowrishankar-infra/sablineRun code an AI wrote without handing it everything you can reach.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Velaris @gowrishankar-infra/velarisWrite Velaris, audit what it can touch, and run it under an effect budget.Not assessed yet.Runs on your machine, installed from PyPI.4 GitHub stars.
- codecalc @the-40-thieves/codecalcCode & logic calculator for AI agents: 31 languages, symbolic math, SMT/logic solving, Big-O.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Workflow MCP @juliusolsson05/workflow-mcpSession-bound Docker workflow server through Codex. State is discarded with the container.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.4 GitHub stars.
- Helmdeck @tosin2013/helmdeckSelf-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Nexus @j7an/nexus-mcpDelegate tasks to coding agents (Claude, Codex, Antigravity) from any MCP client9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- MCP Virtual Computer @flujo-app/mcp-virtual-computerA persistent Docker or Fly computer with a Three.js interface and optional live Xfce desktop.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Parselbox @thesanjeetc/parselboxSecure Python sandbox — MCP servers, APIs, shells and host functions as native Python objects.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- MCP Sandbox Computer VM for AI @flujo-app/mcp-sandbox-computer-vm-for-aiNamed Docker and Fly Machine sandbox computers with an interactive MCP App dashboard.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Pibox @psyb0t/piboxSelf-hosted MCP server: pi-coding-agent tools (run_prompt, file ops) over streamable HTTP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Signalfuse @hypeprinter007-stack/signalfuse11 tools: crypto signals, sentiment, macro regime, arena, search, exec. x402 pay-per-call.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Codex Bridge @hampsterx/codex-mcp-bridgeWraps Codex CLI as MCP tools: codex, review, query, search, structured, ping, listSessions.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- ACMS @gattjoe/acmsApple Container MCP Server (ACMS) provides access to Apple's container CLI tool on macOS6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- OVH @davidlandais/ovh-api-mcpMCP server for the OVH API. Explore and call any OVH endpoint via sandboxed JS.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- LaTeX @sepinetam/latex-mcpEnable AI agents to compile TeX files with LaTeX inside a Docker container.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- agentpc @pawanpaudel93/agentpcInstant, resettable Windows, Ubuntu and Arch Linux ARM desktop VMs for AI agents on Apple Silicon.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Figma Bridge @kolganovr/figma-mcp-bridgeWrite to a live Figma canvas, get a screenshot back, and roll back mistakes. Zero deps, free plan.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Google Jules @georgeracu/google-jules-mcp-serverModel Context Protocol server for Google's Jules AI coding agent7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Hyper @tuananh/hyper-mcp📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- No Crd @nogoo9/no-crdDynamic pod spawner & proxy for ephemeral AI agent workspaces on Kubernetes without CRDs6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Reverse Engineering @daedalus-io/mcp-reverse-engineeringA sandboxed MCP tool for reverse engineering with multiple tool integrations7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Opa Authz @kanywst/mcp-opa-authzAuthorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Sandbox Env MCP @hs3434/sandbox-env-mcpPersistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
