Search: sandbox
Search MCP servers and agent skills by name, description, category or topic — 28 results.
NVIDIA/NemoClaw/nemoclaw-user-manage-sandboxes
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, netw...
NVIDIA/NemoClaw/nemoclaw-user-monitor-sandbox
Inspects sandbox health, traces agent behavior, and diagnoses problems.
cloudflare/sandbox-sdk
Build sandboxed applications for secure, isolated code execution on Workers
alfonsograziano/node-code-sandbox-mcp
A Node.js MCP server that spins up isolated Docker-based sandboxes for executing JavaScript snippets with on-the-fly npm dependency installation and clean teardown
asif-nvc/e2b-sandbox-mcp
Connect Claude Code with E2B cloud sandboxes — 29 tools for creating isolated Linux VMs, cloning repos, running commands, managing files, and performing git operations without touching the local machine.
pydantic/pydantic-ai/mcp-run-python
Run Python code in a secure sandbox via MCP tool calls
NVIDIA/NemoClaw/nemoclaw-user-get-started
Installs NemoClaw, launches a sandbox, and runs the first agent prompt.
NVIDIA/NemoClaw/nemoclaw-user-manage-policy
Adds, removes, or modifies allowed endpoints in the sandbox policy.
NVIDIA/NemoClaw/nemoclaw-user-overview
Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw ve...
NVIDIA/NemoClaw/nemoclaw-user-reference
Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox.
mavdol/capsule/mcp-server
Run untrusted Python/JavaScript code in WebAssembly sandboxes.
stabgan/openrouter-mcp-multimodal
All-in-one multimodal MCP for 300+ OpenRouter models: text chat, image / audio / video analysis, and image / audio / video generation (Veo 3.1, Sora 2 Pro, Seedance, Wan). Structured `_meta.code` error taxonomy, IPv4+IPv6 SSRF guards, path-sandbox for disk writes, retry-after-aware backoff, multi-arch Docker.
r33drichards/mcp-js
A Javascript code execution sandbox that uses v8 to isolate code to run AI generated javascript locally without fear. Supports heap snapshotting for persistent sessions.
PsChina/deepseek-as-subagent
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) in a sandboxed workspace, not just a single LLM call. Includes token-based command sandbox, pre-flight web-search pattern, and cross-platform installer.
yepcode/mcp-server-js
Execute any LLM-generated code in a secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages
telleroutlook/agentkit-js/mcp-server
Code-mode MCP server: collapses N user-defined tools into a two-tool surface (`execute_code` + `docs_search`). Backed by a unified capability manifest (`allowedHosts` / `cpuMs` / `memoryLimitBytes`) honoured across three sandbox kernels — in-process node:vm, WASM (QuickJS / Pyodide / Wasmtime), and remote microVM (E2B / Cloudflare Sandbox). Token-saving benchmark in repo CI.
capsulerun/bash
Sandboxed bash for agents. Run untrusted commands in WebAssembly sandboxes with no setup required.
gerard-kanters/mcp-linux-tools
Administer a Linux server from an MCP client such as Cursor or VS Code: read files and tail logs, check/reload/restart systemd services, manage cron jobs inside a dedicated crontab section, run read-only MySQL queries, drive WP-CLI on WordPress sites, run safe Git commands, and execute sandboxed Python. Directories, services and WordPress sites are allowlisted in `config.json`, and every tool retu
chrassy/klanex-mcp
Reliable async execution for agent tool calls: schema-gate hallucinated payloads before they run, absorb rate limits and outages with retries/backoff/circuit breakers, idempotency keys, human approval gates, encrypted credentials, replay, and signed-webhook results. Errors come back with an `llm_hint` the agent can self-correct from. Hosted remote (`api.klanexai.com/mcp`, free sandbox) or `npx -y
hampsterx/claude-mcp-bridge
Wraps Claude Code CLI as MCP tools (query, search, structured, sessions) with subscription-first auth, cost metadata, budget caps, and granular tool sandboxing.
Vivekpatil200320/CyberRescue
Secure host-level telemetry gateway enabling sandboxed AI agents to dynamically fetch container logs and track kernel resource metrics.
nonameuserd/paybond-kit
Tenant-bound MCP server for agent spend authorization, policy guardrails, evidence, escrow settlement, and portable receipts. Sandbox bootstrap, spend intents, and completion validation for Cursor and Claude Code. TypeScript: `npx -p @paybond/kit paybond login` then `npx -y -p @paybond/kit paybond-mcp-server`. Python: `pip install paybond-kit` then `paybond-kit-login` and `paybond-mcp-server`. [Do
eliottreich/taskbounty-mcp-server
MCP server for [TaskBounty](https://www.task-bounty.com). AI agents fix GitHub bugs (every fix ships with a regression test) and raise test coverage on your codebase. Posters draft and fund bounties from chat (Stripe Checkout); solvers submit PRs verified end-to-end in a sandbox. Paid in USDC, ETH, or BTC. 11 tools.
davidlandais/ovh-api-mcp
Code Mode MCP server for the entire OVH API. Two tools (search + execute) give LLMs access to all OVH endpoints via sandboxed JavaScript, using ~1,000 tokens instead of thousands of tool definitions.
radmail-ai/radmail-mcp
Email operating system for agents: a `search` tool to find the one message by sender/subject/content (no filesystem grep), two-axis triage (importance × urgency), an explainable "Right Now" lane, commitment follow-through, and reviewable drafts. A machine-verifiable hard-stop keeps money/banking-change/first-contact human-only (BEC defense). Zero-auth HTTP sandbox at radmail.ai/api/mcp/sandbox — n
salwks/mcp-techTrend
Multi-source academic + code + medical-regulatory trend monitoring (arXiv, PubMed, GitHub, Hugging Face, openFDA 510(k)/Recalls). Newspaper-style briefings, per-domain tuning, sandbox-safe Python launcher.
hypeprinter007-stack/signalfuse-mcp
11 tools for AI trading agents: fused crypto signals (10 assets), sentiment, macro regime, live strategy arena (4 strategies × 4 assets), fused web search (Brave + Tavily), and sandboxed code execution (E2B). Pay-per-call USDC on Base via x402. Free browser playground at [signalfuse.co/play](https://signalfuse.co/play) — 25 calls/day, no wallet. `npx -y signalfuse-mcp`
endorhq/cli
Endor lets your AI agents run services like MariaDB, Postgres, Redis, Memcached, Alpine, or Valkey in isolated sandboxes. Get pre-configured applications that boot in less than 5 seconds.