mcp_python_exec_server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp_python_exec_servercalculate the average of [1,2,3,4,5]"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Python安全沙箱执行工具 (Python Safe Sandbox Execution Tool)
中文文档
功能描述
这是一个安全的Python代码执行工具,通过MCP服务器提供安全的执行环境。用户可以通过该工具执行Python代码片段,并获取执行结果。该工具禁用了危险的内置函数和模块,以防止恶意代码执行。
支持的标准库
math: 数学计算
statistics: 统计计算
decimal: 高精度小数
fractions: 分数运算
functools: 函数工具
random: 随机数生成
string: 字符串处理
time: 时间相关
datetime: 日期时间
json: JSON处理
re: 正则表达式
禁用功能
以下内置函数被禁用:
eval,exec,open,input,globals,localsbreakpoint,compile,delattr,setattrexit,quit,help,memoryview,vars,dir
使用示例
调用该工具的MCP函数名为python_exec,参数为字符串类型的Python代码。
# 计算1+1
print(1+1)返回结果:
输出:
2如果定义了变量:
a = 10
b = 20
c = a + b
c返回结果:
输出:
30
定义的变量/函数:
a = 10
b = 20
c = 30注意事项
代码必须是字符串类型
代码不能为空
该工具不能执行文件操作、网络请求等危险操作
如果代码执行出错,将返回错误信息
This server cannot be deployed
Maintenance
Related MCP Connectors
Run Python code in a secure sandbox without local setup. Declare inline dependencies and execute s…
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.
Run Python code from natural language prompts, with optional PyPI package install.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA secure server that enables code execution in isolated Docker environments, supporting Python with strict security constraints including network isolation, limited filesystem access, and resource limitations.-
- -licenseNot gradedqualityNot gradedmaintenanceEnables Python code execution in a sandboxed environment with virtual file system management and pip package installation capabilities.-
- AlicenseNot gradedqualityAmaintenanceProvides sandboxed code execution for AI agents with support for Python, JavaScript, and shell commands. Includes comprehensive safety features like destructive pattern blocking, timeout protection, and restricted file access for secure production use.9 npm65 PyPIMIT
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to execute Python code securely in a sandboxed environment. Supports configurable restrictions like no network access and returns results including files.MIT