Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Python Exec Sandbox

PYPI · MCP-PYTHON-EXEC-SANDBOX · SCANNED SEP 24

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

0 this week 0 Trust /100

Recent critical change

CVE-2026-32871 affects this package (4 Aug 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

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 Security25
Provenance & Transparency32
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 575 tokens (~191/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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_python" 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 3 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
Install

How do I install the Python Exec Sandbox MCP server?

Python Exec Sandbox runs locally as a PyPI package, launched with uvx mcp-python-exec-sandbox. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · mcp-python-exec-sandbox

# add to Claude Code
claude mcp add lu-zhengda-mcp-python-exec-sandbox -- uvx mcp-python-exec-sandbox
// .cursor/mcp.json
{
  "mcpServers": {
    "lu-zhengda-mcp-python-exec-sandbox": {
      "command": "uvx",
      "args": [
        "mcp-python-exec-sandbox"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "lu-zhengda-mcp-python-exec-sandbox": {
      "command": "uvx",
      "args": [
        "mcp-python-exec-sandbox"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add lu-zhengda-mcp-python-exec-sandbox -- uvx mcp-python-exec-sandbox
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lu-zhengda-mcp-python-exec-sandbox": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-python-exec-sandbox"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add lu-zhengda-mcp-python-exec-sandbox --command uvx --arg mcp-python-exec-sandbox
# ~/.hermes/config.yaml
mcp_servers:
  lu-zhengda-mcp-python-exec-sandbox:
    command: "uvx"
    args: ["mcp-python-exec-sandbox"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "lu-zhengda-mcp-python-exec-sandbox": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-python-exec-sandbox"
      ]
    }
  }
}
# add to Vellum
assistant mcp add lu-zhengda-mcp-python-exec-sandbox -t stdio -c uvx -a mcp-python-exec-sandbox
// mcp.json
{
  "mcpServers": {
    "lu-zhengda-mcp-python-exec-sandbox": {
      "command": "uvx",
      "args": [
        "mcp-python-exec-sandbox"
      ]
    }
  }
}
Changelog

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.

  • 24 Sept 26 0
    • Stability: pass → 0.83 functional
  • 23 Sept 26 0
    • Stability: 0.97 → pass security
  • 22 Sept 26 0
    • Malware scan: pass → unverified ▼ security
  • 21 Sept 26 0
    • Malware scan: unverified → pass ▲ security
  • 18 Sept 26 0
    • Malware scan: pass → unverified ▼ security
    • Security disclosure: unverified → fail ▼ functional
  • 17 Sept 26 0
    • Malware scan: unverified → pass ▲ security
    • Security disclosure: fail → unverified ▼ functional
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 0
    • Security disclosure: unverified → fail ▼ functional
Diagnostics

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 24 Sept 2026 · Analysed pypi/mcp-python-exec-sandbox@0.1.5

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Vulnerabilities 6 findings
ID CVE Severity Vector Fix available
GHSA-m8x7-r2rg-vh5g CVE-2025-64340 medium CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H yes
GHSA-rww4-4w9c-7733 CVE-2026-27124 high yes
GHSA-vv7q-7jx5-f767 CVE-2026-32871 critical CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H yes
PYSEC-2026-2475 CVE-2025-64340 medium CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H yes
PYSEC-2026-2476 CVE-2026-27124 none yes
PYSEC-2026-338 CVE-2026-32871 critical CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 76 packages
Packages resolved 76
Stale 5
No linked repository 3
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 3 exposed · ~575 tokens

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 →

Tool Tokens
check_environment ~34

Check the execution environment and report status. Returns information about Python version, uv version, platform, sandbox configuration, and cache status.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

execute_python ~404

Execute a Python script with automatic dependency management. The script can include PEP 723 inline metadata (# /// script blocks) for declaring dependencies. Additional dependencies can also be passed via the dependencies parameter and will be merged. Args: script: Python source code to execute. May include PEP 723 metadata. dependencies: Extra PEP 508 dependency specifiers to make available. timeout_seconds: Maximum execution time (1-300, default 30). Returns: Formatted output with stdout, stderr, exit code, and duration. Example - simple script: execute_python(script="print('hello')") Example - with dependencies parameter: execute_python( script="import requests; print(requests.get('https://example.com').status_code)", dependencies=["requests>=2.32"] ) Example - with inline dependency metadata (preferred for multiple deps): execute_python(script=''' # /// script # dependencies = ["pandas>=2.2", "numpy>=1.26"] # /// import pandas as pd import numpy as np print(pd.DataFrame({"a": np.arange(5)}).describe()) ''') Always pin dependency versions (e.g. "pandas>=2.2" instead of "pandas") for reproducible results. The inline metadata block (# /// script ... # ///) is the recommended way to declare dependencies directly in the script (see PEP 723: https://peps.python.org/pep-0723/). The dependencies parameter is a simpler alternative when you just need to add a few packages. Both accept standard pip-style version specifiers like "requests>=2.28" or "pandas" (see PEP 508: https://peps.python.org/pep-0508/).

NameTypeReqDescription
dependencies–––
scriptstringyes–
timeout_secondsinteger––
NameTypeReqDescription
resultstringyes–

No examples provided.

validate_script ~137

Validate a Python script's PEP 723 metadata and dependencies without executing it. Checks metadata syntax, dependency format, and requires-python compatibility. Args: script: Python source code to validate. May include inline dependency metadata (# /// script blocks, see https://peps.python.org/pep-0723/). dependencies: Extra dependency specifiers to validate, using standard pip-style format like "requests>=2.28" (see https://peps.python.org/pep-0508/). Returns: Validation result with metadata details or error information.

NameTypeReqDescription
dependencies–––
scriptstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

Common questions

What is the Python Exec Sandbox MCP server?

Python Exec Sandbox is an MCP server listed in the public MCP registry as io.github.lu-zhengda/mcp-python-exec-sandbox. Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution. This page covers its PyPI package (mcp-python-exec-sandbox).

What tools does the Python Exec Sandbox MCP server expose?

Python Exec Sandbox exposes 3 tools: execute_python, check_environment, validate_script. Their descriptions and schemas cost roughly 575 tokens of context every time the server is loaded.

Is the Python Exec Sandbox MCP server still maintained?

Python Exec Sandbox is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.