Analyze code and provide refactoring suggestions
AI agents call refactor_code to retrieve information from Shell Executor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool analyzes existing code and returns suggestions—a read-only operation. Despite being on a 'Shell Executor' server with dangerous siblings like 'execute_command', this particular tool does not execute commands, modify data, or trigger external operations. It retrieves and processes code to generate recommendations, classifying it as Read.
From the tool's definition Tool name 'refactor_code' and description 'Analyze code and provide refactoring suggestions' indicate analysis and recommendation generation with no code execution, data modification, or side effects.
Attacks that exploit this kind of access
Analyze code and provide refactoring suggestions. It is categorised as a Read tool in the Shell Executor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Shell Executor MCP Server MCP server in PolicyLayer and add a rule for refactor_code: 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 Shell Executor MCP Server. Nothing to install.
refactor_code 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 refactor_code 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 refactor_code. 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.
refactor_code is provided by the Shell Executor MCP Server MCP server (kosiew/zmcp). 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 →