- EQVPS — VPS and code sandboxes for AI agents @poiuyhje/eqvpsNo-KYC VPS + per-second code sandboxes AI agents run over MCP — 75 tools, SDK, pay BTC/XMR/USDC/USDT13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Code Sandbox API @br0ski777/code-sandboxExecute Python, JavaScript, SQL code in a sandbox. x402 micropayment.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Prover @axiomatic-ai/proverLean 4 MCP server: compile, prove theorems, and formalize math with Mathlib.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Premiss @founders-loralabs/premissCreate Python strategies and backtest crypto, stocks and ETFs in Claude. Premiss account required.Not assessed yet.A remote server; no sign-in.
- Shardflux @shardflux/mcpPersistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AgentSpace @agentspace/agentspaceGive your agent a persistent workspace: files, a code sandbox and a public URL to publish to.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Batcave Agent Services @bjorn2-sol/batcave-agent-servicesMCP discovery and x402 checkout handoff for five paid Batcave agent products.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sandboxd Code Run @saastemly/sandboxd-code-runHosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit...8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SecureStamp Action Proof — Cross-Cloud Public Beta (Unverified) @securestamp/action-proofUNVERIFIED: cross-cloud beta; sandbox by default; production opt-in via customer Guardian.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- NIRA REPL MCP @pachote/nira-replSecure code execution sandbox for Claude — run Python, JavaScript, and shell commands10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Ovrin @joshluberisse/ovrin-mcpSecure Linux sandboxes for AI agents, as MCP tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Vending Factory @rubentay/agent-vending-factoryPay-per-call MCP tools via x402 USDC: ZAR prices, data extraction, Python sandbox, SA flights.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Alpacacloud @melgencer/alpacacloud-mcpConnect AI agents to Alpaca Cloud: Postgres, Auth, Storage, Sandboxes, and Workflows.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Bedc @be-dce/bedc-mcpMCP server for Dual Canvas Execution (DCE) - use with Polsia, Cursor, Claude, and other MCP clients9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gibil @alexikm/gibilSpawns an ephemeral Ubuntu VM with project clone, shell exec, file I/O, and auto-destroy on TTL.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AIAgora @aiagora/agoraOpen square for AI agents: solve sandbox-tested problems, earn Ed25519-signed proofs.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- cdbx.ai MCP @cdbx/mcp-serverBuild Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- agent-exec @448c/agent-execAccountless pay-per-use sandbox, storage, locks, attestation and handoff. Paid over MCP with x402.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Foundry MCP code mode @foundry-mcp/foundry-codeCode mode (preview): the AI writes a script against a typed foundry.* API and runs it in a sandbox.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Code Interpreter Agent by Nova (CIVAI) @civai/code-interpreter-agentI do everything related to coding and execution tasks8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Pebble @shippebble/pebbleHost the tools your AI builds — small internal tools in isolated microVMs, live for your team.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- GardenArena GardenScript @gardenarena/gardenscriptSimulate farms, validate GardenScript and compare policies with Rust. No outbound LLM calls.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- CinderRoute Agent Exchange @cinderroute/agentic-ci-operationsCinderRoute Agent Exchange for public failed-build triage, artifact handoff, and remediation.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Python Package Runtime Test @ligafew/python-package-runtime-testHosted Python sandbox for package runtime verification: pip install and usable-import evidence.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
