LLM Sandbox

io.github.vndee/llm-sandboxv0.3.42Docker & Containers

Securely run LLM-generated code in isolated containers across 7 languages and 4 backends.

In-path gate · all MCP tools

Using LLM Sandbox in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-09-01 19:02 UTC

screened 2026-08-02tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No malicious intent described”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-08-02).

Contracts can change after screening, with no version bump. The gate pins LLM Sandbox’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-vndee-llm-sandbox)](https://mcpindex.ai/server/io-github-vndee-llm-sandbox)

HTML

<a href="https://mcpindex.ai/server/io-github-vndee-llm-sandbox"><img src="https://mcpindex.ai/api/v1/badge/io-github-vndee-llm-sandbox" alt="mcpindex verdict" height="20" /></a>

Environment variables

BACKEND

Container backend to use. Must match the installed extra: mcp-docker, mcp-podman, or mcp-k8s.

DOCKER_HOST

Docker or Podman socket URL, e.g. unix:///var/run/docker.sock

KUBECONFIG

Path to kubeconfig file when BACKEND=kubernetes.

NAMESPACE

Kubernetes namespace used for sandbox pods when BACKEND=kubernetes.

COMMIT_CONTAINER

Commit the container after a run so installed libraries persist between sessions.

KEEP_TEMPLATE

Keep the base image after the session ends to avoid re-pulling it on the next run.

SANDBOX_NETWORK_MODE

Network mode for the sandbox container. Set to 'none' for hardened isolation. Docker and Podman backends only.

SANDBOX_READ_ONLY

Mount the sandbox root filesystem read-only. Recommended: true. Docker and Podman backends only.

SANDBOX_CAP_DROP

Comma-separated Linux capabilities to drop. Recommended: ALL. Docker and Podman backends only.

SANDBOX_SECURITY_OPT

Comma-separated container security options, e.g. no-new-privileges. Docker and Podman backends only.

SANDBOX_MEMORY

Memory limit for the sandbox container, e.g. 4g. Docker and Podman backends only.

SANDBOX_CPUS

Fractional CPU allocation for the sandbox container, e.g. 1.5. Docker and Podman backends only.

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Docker & Containers

Cortex RMCP

ai.dinglebear/cortex-rmcp

Rust MCP server for homelab logs, syslog, Docker logs, FTS search, and AI transcript correlation.

Arcane RMCP

ai.dinglebear/arcane-rmcp

Rust MCP server and CLI for Arcane Docker and container management.

SearXNG HTTP MCP

io.github.whw23/searxng-http-mcp

Self-contained SearXNG metasearch MCP server. One Docker image, 200+ engines, privacy-first.

Install this server

Claude Desktop (uvx)

{
  "mcpServers": {
    "llm-sandbox": {
      "command": "uvx",
      "args": [
        "--",
        "llm-sandbox"
      ],
      "env": {
        "BACKEND": "docker",
        "DOCKER_HOST": "<docker_host>",
        "KUBECONFIG": "<kubeconfig>",
        "NAMESPACE": "default",
        "COMMIT_CONTAINER": "true",
        "KEEP_TEMPLATE": "true",
        "SANDBOX_NETWORK_MODE": "<sandbox_network_mode>",
        "SANDBOX_READ_ONLY": "<sandbox_read_only>",
        "SANDBOX_CAP_DROP": "<sandbox_cap_drop>",
        "SANDBOX_SECURITY_OPT": "<sandbox_security_opt>",
        "SANDBOX_MEMORY": "<sandbox_memory>",
        "SANDBOX_CPUS": "<sandbox_cpus>"
      }
    }
  }
}

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-vndee-llm-sandbox

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.3.42
category: Docker & Containers
verdict expires: 2026-09-01
quality: 90 / 100
operator: vndee

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 960,209). Verify it yourself.

Links

Repository →Website →