Sandboxd Code Run vs LLM Sandbox
Sandboxd Code Run is an MCP server published by saastemly.com. Marketplaces we read that list it: 1 (Official MCP Registry). LLM Sandbox is an MCP server published by vndee. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-25. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  LLM Sandbox | |
|---|---|---|
| Official MCP Registry | Listed Version: 1.0.1791044057 No figure published Not marked · First seen |
Listed Version: 0.3.43 Downloads/month (PyPI): 353 353 Downloads/week (PyPI): 101 579 Forks (GitHub): 107 Stars (GitHub): 1 137 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | Sandboxd Code Run | LLM Sandbox |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | No figure on GitHub | 1 137 |
| Forks (GitHub) (differs) | No figure on GitHub | 107 |
| Last release | Not published | Not published |
| Where it runs (differs) | Remote server (sandboxd-code-run.saastemly.com/mcp) | On your machine (llm-sandbox) |
| Transport (differs) | Streamable HTTP | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 12, secrets among them: 0 |
| Licence | Not stated | Not stated |
| Repository (differs) | Not stated | github.com/vndee/llm-sandbox |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | Responded 6 days ago | no remote endpoint we check |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
Sandboxd Code Run
Hosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit...
LLM Sandbox
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
How to run each
Sandboxd Code Run As a remote MCP server
claude mcp add --transport http sandboxd-code-run https://sandboxd-code-run.saastemly.com/mcp --header "Authorization: Bearer <YOUR_TOKEN>"Requires: Authorization header
LLM Sandbox As a local MCP server: PyPI package
claude mcp add --transport stdio llm-sandbox -- uvx --from "llm-sandbox[mcp-docker]" llm-sandboxCommands built only from what the marketplaces declare; the full set for every client is on each card.
Only Sandboxd Code Run has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of Sandboxd Code Run publish no settings it asks for, so we do not compare settings.
What it can do: Sandboxd Code Run · What it can do: LLM Sandbox · Compare two other plugins
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.