- Eterna MCP @eternahybridexchange/eterna-mcpNo-KYC managed MCP for AI agents: sandboxed TypeScript trading SDK, isolated sub-accounts, futures.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.11 GitHub stars.
- Sevalla @sevalla-hosting/mcpOfficial Sevalla MCP — full PaaS API access through just 2 tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.8 GitHub stars.
- Pymcp @smithery/anirbanbasu-pymcpPrimarily to be used as a template repository for developing MCP servers with FastMCP in Python, P…6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.8 GitHub stars.
- EasyBits @easybits/easybitsPersistent Linux microVMs for agents: root, internet, sub-second resume and a public URL.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7 GitHub stars.
- Blinkbox @blinkboxhq/blinkboxOpen-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Aziel Runtime @azieleliab/aziel-runtimeGoverned MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- OpenCode MCP Bridge @manuotel/opencode-mcp-bridgeCoordinate and verify OpenCode workers over MCP Streamable HTTP.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News @its-fortunatefolly/hubvibe70+ pay-per-call tools for AI agents: web search, email verify, KYC, stocks, crypto, news, data8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- ArcAgent MCP @araujota/arcagent-mcpArcAgent MCP server for bounty discovery, workspace execution, and verified coding submissions.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
- SandboxAPI @michielderuiter/sandboxapi-mcpExecute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.2 GitHub stars.
- Itamos MCP Tools @itamos-technologia/itamos-mcp-toolsCode-map tools for AI agents: see a repo's structure first, then edit only what matters.Not assessed yet.A remote server; you sign in with your account.1 GitHub stars.
- Rokha @rokha/rokhaSearch a registry of agent skills and MCP servers, then run them for real. No install, traced.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Runtime Cloud @withruntime/runtimeLinux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- FetchSandbox @fetchsandbox/mcpA deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Sprites MCP Server @sprites/mcpManage Sprites: sandboxed compute environments with exec, services, and checkpoints.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Kael MCP Server @dreamingms/kael-mcp-server16 AI-native tools with dual SSE + streamable-http transport. Free tier available.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Burrowbox @burrowbox/burrowboxPersistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Symbioza @symbioza/symbiozaRun a GPU job under a hard dollar cap and collect the files it writes.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ParallelSandbox @parallelsandbox/parallelsandboxRemote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Ebook File Check @powmcp/epub-checkRun EPUBCheck for EPUB specification errors and compare two exports.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Mcphost @mcphost/mcphostHosted MCP runtime where your agent publishes its own tools by tool call and keeps working.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
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.
107 remote200 localTagged by Odel's AI, which can make mistakes
Most popular in Code execution sandboxes
By GitHub stars, at most two per publisher- Number 1: Superserve@superserve-ai/mcpMCP server for Superserve sandboxes: create, exec, and manage Firecracker microVMs9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.465 GitHub stars.
- Number 2: Memory Journal@smithery/neverinfamous-memory-journal-mcpA MCP server built for developers enabling Git based project management with project and personal…16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.20 GitHub stars.
- Number 3: Chiplab@veecle/chiplabRun, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.17 GitHub stars.
