Read a file from the sandbox workspace.
AI agents call read_workspace_file 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 data (file contents) from a sandboxed workspace without modifying, deleting, or executing anything. It is a straightforward read operation. The sandbox environment further limits risk. Severity is low because the blast radius of misuse is limited to information disclosure of files already within the sandbox, and no destructive or code execution capabilities are involved.
From the tool's definition Tool name is 'read_workspace_file' and description states 'Read a file from the sandbox workspace.' The verb 'read' and the explicit statement of retrieving file content indicate a query operation with no side effects.
Attacks that exploit this kind of access
Read a file from 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 read_workspace_file: 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.
read_workspace_file 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 read_workspace_file 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 read_workspace_file. 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.
read_workspace_file 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 →