Refatora um arquivo de código conforme instruções.
AI agents use refactor_code to create or update resources in MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Server environment.
Refactoring modifies existing source code files in place according to provided instructions. This is a Write operation as it alters file contents, though it is generally reversible via version control. The severity is high because an AI agent could make sweeping, unintended changes to source files across a codebase if misused or given broad instructions.
From the tool's definition Refatora um arquivo de código conforme instruções (Refactors a code file according to instructions)
Attacks that exploit this kind of access
Refatora um arquivo de código conforme instruções. It is categorised as a Write tool in the MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 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 MCP Server. Nothing to install.
refactor_code is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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 MCP Server MCP server (kelvis-santos/mcp-vscode-examples). 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 →