LLM Sandbox
PYPI · LLM-SANDBOX
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
Available components
Last scanned (14 hours ago)
Scores higher than 78% of PyPI servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency35
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 36 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 215 tokens (~53/item across 4 items; 3 tools + 1 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_code" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- License in Provenance & TransparencyLicence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 20 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 19 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 18 Nov 26 −16
- Malware scan: pass → unverified ▼ security
- Stability: pass → 0.97 functional
- 17 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 16 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 15 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 12 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed pypi/llm-sandbox@0.3.43
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
execute_code ~115
Execute code in a secure sandbox environment and automatic visualization capture. Args: code: The code to execute language: Programming language (python, javascript, java, cpp, go, r, ruby) libraries: List of libraries/packages to install timeout: Execution timeout in seconds (default: 30) Returns: List of content items including execution results and any generated visualizations
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| language | string | – | – |
| libraries | – | – | – |
| timeout | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
get_language_details ~48
Get the details of a language. Args: language: The language to get the details of Returns: TextContent: The details of the language
| Name | Type | Req | Description |
|---|---|---|---|
| language | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| _meta | – | – | – |
| annotations | – | – | – |
| text | string | yes | – |
| type | string | yes | – |
No examples provided.
get_supported_languages ~28
Get the list of supported languages. Returns: TextContent: The list of supported languages
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| _meta | – | – | – |
| annotations | – | – | – |
| text | string | yes | – |
| type | string | yes | – |
No examples provided.
How do I install the LLM Sandbox MCP server?
LLM Sandbox runs locally as a PyPI package, launched with uvx --from 'llm-sandbox[mcp-docker]' llm-sandbox. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
pypi · llm-sandbox
claude mcp add vndee-llm-sandbox -- uvx --from 'llm-sandbox[mcp-docker]' llm-sandbox
What is the LLM Sandbox MCP server?
LLM Sandbox is an MCP server listed in the public MCP registry as io.github.vndee/llm-sandbox. Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends. This page covers its PyPI package (llm-sandbox).
Is the LLM Sandbox MCP server safe to use?
LLM Sandbox scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the LLM Sandbox MCP server expose?
LLM Sandbox exposes 3 tools: execute_code, get_supported_languages, get_language_details. Their descriptions and schemas cost roughly 191 tokens of context every time the server is loaded.
Is the LLM Sandbox MCP server still maintained?
LLM Sandbox is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the LLM Sandbox MCP server?
VerifyMCP ran 15 checks on LLM Sandbox, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about LLM Sandbox: License. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.