LLM Sandbox
MCP-Server · vndee
- Auf Ihrem Rechner
LLM Sandbox ist ein MCP-Server von vndee. Marktplätze, die wir lesen und die es listen: 1 (Official MCP Registry). Wir haben es erstmals am 2026-10-11 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-11.
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
- Marktplätze
- 1
- Wo es läuft
- Auf Ihrem Rechner
llm-sandbox - Größte veröffentlichte Zahl
- 1 130 Sterne (GitHub) · Official MCP Registry
- Erstmals gesehen
- 2026-10-11
- Letzte Änderung
- Keine erfasst
- Verifiziert-Markierung
- Nicht markiert
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Official MCP Registry (Eintrag in der Registry öffnen) | Gelistet | 0.3.43 | Forks (GitHub): 107 Sterne (GitHub): 1 130 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
Was es kann
Läuft auf Ihrem Rechner: Das KI-Tool startet dieses PyPI-Paket lokal: llm-sandbox
- Deklarierte Tools
- Nicht veröffentlicht
- Abgefragte Umgebungsvariablen
- 12 davon Geheimnisse: 0
Was sich geändert hat
Bei diesem Plugin hat sich nichts bewegt, seit wir es beobachten.
Der Herausgeber
vndee · Repository: github.com/vndee/llm-sandbox
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
- ScratchRunEphemeral MicroVM-isolated code execution for AI agents. Fresh VM per call, hard-purged after.
- ZenBridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
- Sandboxd Code RunHosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit...
- Code Interpreter Agent by Nova (CIVAI)I do everything related to coding and execution tasks
- NIRA REPL MCPSecure code execution sandbox for Claude — run Python, JavaScript, and shell commands
- Tenki Sandbox MCPDisposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
- Session ForgePersistent memory and session intelligence for AI coding assistants. Zero config.
- Node.js SandboxA Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
- HackerEarth MCPGive any AI assistant a code run button via HackerEarth. 24 languages, zero setup.
- misterdev io.github.dcondrey/misterdevAutonomous LLM build orchestrator that plans, edits, and verifies code across languages.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
- sniparaContext optimization + safe code execution - Query docs (90% token reduction), orchestrate multi-round exploration, and execute code with Docker isolation using RLM Runtime
- llm-gatewayMulti-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job orchestration, and token optimization.
- nexus-agentsIntelligent orchestration platform for AI coding tools. Coordinates Claude, Codex, Gemini, and OpenCode through a single MCP server — routing each task to the best model using…
- iloWrite, run, debug, and explain programs in ilo — a token-optimised programming language for AI agents
- together-ai-skillsA collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch…
Gelistet auf Claude Code: claude-plugins-official (5)
- appwriteAppwrite tools for Claude Code, including SDK skills, Appwrite MCP servers, and deployment commands.
- claude-code-setupAnalyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
- Endor Labs Agent KitSet up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
- lumenPrecise local semantic code search via MCP. Indexes your codebase with Go AST parsing, embeds with Ollama or LM Studio, and exposes vector search to Claude through an MCP server…
- Desktop CommanderMCP server for terminal commands, file operations, and process management
Gelistet auf Claude: knowledge-work-plugins (5)
- Desktop CommanderMCP server for terminal commands, file operations, and process management
- renderDeploy, debug, and monitor applications on Render. Includes skills, an agent, slash commands, and a render.yaml validation hook.
- buildkiteOfficial Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
- security-guidanceSecurity review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
- QodoBring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
- OpenAI DevelopersBuild with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
- Plugin EvalEvaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
- NVIDIASkills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
- CodeRabbitAI-powered code review in Codex, powered by CodeRabbit.
- GitHubInspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
Gelistet auf Community GitHub marketplaces (5)
- Dash0 ObservabilityOpenTelemetry observability for OpenAI Codex sessions. Captures prompts, tool calls, MCP calls, sub-agent activity, and token usage as OTel traces.
- Endor Labs Agent KitEndor Labs workflow agents and setup for Claude Code.
- appwriteAppwrite tools for Claude Code, including SDK skills, Appwrite MCP servers, and deployment commands.
- Desktop CommanderMCP server for terminal commands, file operations, and process management
- Endor Labs AI Plugins (Legacy)Legacy Claude Code plugin id for Endor Labs Agent Kit workflows.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
- radiusModel, visualize, and deploy applications with Radius from the GitHub Copilot app and CLI.
- copilot-sdkBuild applications with the GitHub Copilot SDK across multiple programming languages. Includes comprehensive instructions for C#, Go, Node.js/TypeScript, and Python to help you…
- awesome-copilotMeta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
- datadogUse Datadog directly in Copilot / VS Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation.
- noob-modePlain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
Gelistet auf Copilot CLI: github/copilot-plugins (5)
- advanced-securityAdvanced Security plugin for GitHub Copilot.
- microsoft-365-agents-toolkitToolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
- azure-devops-copilot-pluginBring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
- cpp-language-serverNavigate and interact with your C++ code using the Microsoft C++ Language Server.
- canvas-appsBuild Power Apps Canvas Apps using the Canvas Authoring MCP server.
Gelistet auf Cursor: cursor/plugins (5)
- Cursor SDKBuild apps, scripts, and automations with the TypeScript SDK.
- Origin AppsSkills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
- OrchestrateFan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
- Ralph LoopIterative self-referential AI loops using the Ralph Wiggum technique.
- Agent CompatibilityCLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
Gelistet auf Docker MCP Catalog (5)
- ZenBridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
- Node.js SandboxA Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
- E2BGiving Claude ability to run code with E2B via MCP (Model Context Protocol).
- Sequa.AIStop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
- Desktop CommanderMCP server for terminal commands, file operations, and process management
Gelistet auf Official MCP Registry (5)
- ScratchRunEphemeral MicroVM-isolated code execution for AI agents. Fresh VM per call, hard-purged after.
- Sandboxd Code RunHosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit...
- Code Interpreter Agent by Nova (CIVAI)I do everything related to coding and execution tasks
- NIRA REPL MCPSecure code execution sandbox for Claude — run Python, JavaScript, and shell commands
- Tenki Sandbox MCPDisposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Ist das Ihr Plugin?
Weisen Sie nach, dass Sie das Plugin pflegen: mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag. Sie erhalten Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, das Verifiziert-Zeichen oder die angeforderten Angaben ändert, und können den Remote-Endpunkt als Webdienst überwachen lassen.
Daten von Official MCP Registry. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.