// MCP TOOL REFERENCE

MCP SANDBOX TOOLS

7 tools from the MCP Sandbox MCP Server, categorised by risk level.

// ALL 7 MCP SANDBOX TOOLS

READ 2 tools

Read check_package_installation_status Checks the installation status of a package in a sandbox. Parameters: sandbox_id (string), package_name (st... Read list_sandboxes Lists all existing Python sandboxes and their status. Each item also includes installed Python packages.

WRITE 2 tools

Write create_sandbox Creates a new Python sandbox and returns its ID for subsequent operations. Optional parameter: name (string... Write upload_file_to_sandbox Uploads a local file to the specified sandbox. Parameters: sandbox_id (string), local_file_path (string), d...

EXECUTE 3 tools

Execute execute_python_code Executes Python code in a sandbox and returns results with links to generated files. Parameters: sandbox_id... Execute execute_terminal_command Executes a terminal command in the specified sandbox. Parameters: sandbox_id (string), command (string). Re... Execute install_package_in_sandbox Installs a Python package in the specified sandbox. Parameters: sandbox_id (string), package_name (string)

// FAQ

How many tools does the MCP Sandbox MCP server have? +

The MCP Sandbox MCP server exposes 7 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on MCP Sandbox tools? +

Route the MCP Sandbox server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do MCP Sandbox tools fall into? +

MCP Sandbox tools are categorised as Read (2), Write (2), Execute (3). Each category has a recommended default policy.

Enforce policy on every MCP Sandbox tool call.

Start from MCP Sandbox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.