modal_get_sandbox
AI agents call modal_get_sandbox to retrieve information from Modal MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is part of a read-only server designed for inspection without mutation capabilities. The naming convention ('get_') and context among sibling read-only tools (get_app, get_app_logs, get_container_logs, get_environment) strongly indicate this retrieves sandbox information without side effects.
From the tool's definition Tool name 'modal_get_sandbox' and server description explicitly states 'read-only Modal context' that 'Enables agents to inspect Modal apps, deployments, logs, containers, volumes, and sandboxes without granting mutation tools.' No description provided for…
Attacks that exploit this kind of access
modal_get_sandbox. It is categorised as a Read tool in the Modal MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Modal MCP Server MCP server in PolicyLayer and add a rule for modal_get_sandbox: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Modal MCP Server. Nothing to install.
modal_get_sandbox is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the modal_get_sandbox rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for modal_get_sandbox. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
modal_get_sandbox is provided by the Modal MCP Server MCP server (php-workx/modal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →