Code execution sandboxes MCP servers

A server here runs code or commands in an isolated sandbox or container for an AI agent.

Not here: deploying apps to production.

307servers
107 remote200 localTagged by Odel's AI, which can make mistakes

Best fit

182 made for this, ranked by starsRemoteLocal
  1. 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.
  2. 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.
  3. 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.
  4. Batcave Detective Basic @bjorn2-sol/batcave-detectiveEvidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. agent-exec @sslip/agent-execAccountless pay-per-use sandbox execution, storage, locks, attestation and handoff; pay via x402.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. AgentCloud — Hosted iOS Simulator MCP @agentcloud/ios-simulatorBuild, run, and inspect iOS apps in disposable hosted Simulators from cloud coding agents.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  7. Execute chroot-filesystem-jail-mcp @evozim/chroot-filesystem-jail-mcpPremium agentic endpoint for chroot-filesystem-jail-mcp.31% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  8. Verify @kenoodl/verifyRuns your code against a contract; HELD or BROKE at the exact input. Deterministic. 0.10 USDC/call.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. x402 Market Intelligence + Russian Web Access @ruscrape/russia-accessCheck x402 endpoints before paying: liveness, price history, farm detection. Plus RU web access.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.