Secure Python Code Sandbox by Apoth3osis

Name: Secure Python Code Sandbox
Brand: Apoth3osis
SKU: 689f48d98ee2d1dd79e9035e
Price: 0.10 USD
Availability: InStock

Secure Python Code Sandbox

Compute

Details

For safely executing arbitrary Python code snippets within an isolated, secure environment. The sandbox comes pre-installed with common data science and web request libraries, including requests, NumPy, and pandas. It is ideal for performing quick computations, data transformations, or dynamic API calls without requiring external infrastructure.

Use Cases

Dynamic Code Execution, Data Manipulation, On-the-fly Calculation, API Integration, Data Analysis, Custom Scripting, Algorithmic Tasks, Web Scraping

Parameters

2 parameters(required listed first)

view all

coderequiredstring

A string containing the Python code to be executed. The code must be self-contained. Constraints: Maximum of 50,000 characters. Example: "import numpy as np\ndata = np.array([1, 2, 3, 4, 5])\nmean = np.mean(data)\nprint(\"The mean is {}\".format(mean))"

timeout_secondsnumber

The maximum number of seconds to allow the code to run before terminating the execution. Default: 60 Constraints: Must be an integer between 10 and 60.

Range: 10 - 60

Connect Your Agent In 5 Min

Use hosted MCP first, or install the local STDIO fallback when your client requires a command

Hosted Streamable HTTPS

Use the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.

Endpoint: https://api.agentpmt.com/mcp
Authorization: Bearer <AGENTPMT_BEARER_TOKEN>

Full connection guide

Local STDIO Fallback

Use the local router for Claude Code, Codex, Cursor, Zed, and other clients that require a command-based MCP server. The router forwards requests to the hosted endpoint and does not execute tools locally.

npm install -g @agentpmt/mcp-routeragentpmt-setup

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "689f48d98ee2d1dd79e9035e",
    "parameters": {
      "code": "example_code"
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "689f48d98ee2d1dd79e9035e",
    "parameters": {
        "code": "example_code"
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "689f48d98ee2d1dd79e9035e",
  parameters: {
    "code": "example_code"
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "689f48d98ee2d1dd79e9035e",
  parameters: {
    "code": "example_code"
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

Frequently Asked Questions

How do I connect this tool to an external agent?

You can install the local MCP server by opening a terminal and running:

Install commands

npm install -g @agentpmt/mcp-router
agentpmt-setup

This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.

Alternatively you can connect to the hosted version with this config block, no installation required:

Hosted MCP config

{
  "mcpServers": {
    "agentpmt": {
      "type": "streamable-http",
      "url": "https://api.agentpmt.com/mcp",
      "headers": {
        "Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
        "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
      }
    }
  }
}

View MCP Connection Instructions for more details.

How does an external agent use this tool?

After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent:

Agent prompt

Call the AgentPMT-Tool-Search-and-Execution tool with action 'get_schema' and tool_id 689f48d98ee2d1dd79e9035e ("Secure Python Code Sandbox"). Then call the same tool with action 'call_tool', tool_id 689f48d98ee2d1dd79e9035e, and the parameters needed for my request.

The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT.