modal_list_sandboxes
AI agents call modal_list_sandboxes 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 lists sandboxes, which is a retrieval operation. The server is explicitly designed as read-only for inspection purposes. Even though the tool description is empty, the server context and tool name ('list') strongly indicate this is a data query with no mutations or side effects. Listing/inspecting resources carries low risk of misuse—the worst outcome is information disclosure about existing sandboxes.
From the tool's definition Tool name 'modal_list_sandboxes' combined with server description stating 'read-only Modal context' and explicit statement that server 'Enables agents to inspect...sandboxes without granting mutation tools'.
Attacks that exploit this kind of access
modal_list_sandboxes. 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_list_sandboxes: 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_list_sandboxes 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_list_sandboxes 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_list_sandboxes. 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_list_sandboxes 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 →