List files in the sandbox workspace.
AI agents call list_workspace_files to retrieve information from Code Execution MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the contents of a workspace directory without creating, modifying, executing, or deleting any data. It is a read-only operation that returns information about available files. The sandboxed context further limits risk. Severity is low because directory listing poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'list_workspace_files' and description 'List files in the sandbox workspace' indicate a file listing/directory enumeration operation with no modification or execution capability.
Attacks that exploit this kind of access
List files in the sandbox workspace. It is categorised as a Read tool in the Code Execution MCP MCP Server, which means it retrieves data without modifying state.
Register the Code Execution MCP server in PolicyLayer and add a rule for list_workspace_files: 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 Code Execution MCP. Nothing to install.
list_workspace_files 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 list_workspace_files 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 list_workspace_files. 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.
list_workspace_files is provided by the Code Execution MCP server (marc-shade/code-execution-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 →