AI agents call get_code_actions to retrieve information from MCP-TY without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the type checker for available refactoring suggestions at a code location, which is a read-only operation. It returns information about what *could* be done, not what *is* done. The sibling tools like 'apply_code_action' would handle execution; this one only retrieves available options. Classified as Read with low severity due to minimal side effects.
From the tool's definition Tool description states 'Get available quick fixes and refactorings at position' — retrieves information about available actions without executing them. No modification, deletion, or execution of code occurs; it only queries and returns diagnostic suggestions.
Attacks that exploit this kind of access
Get available quick fixes and refactorings at position (1-based). It is categorised as a Read tool in the MCP-TY MCP Server, which means it retrieves data without modifying state.
Register the MCP-TY MCP server in PolicyLayer and add a rule for get_code_actions: 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-TY. Nothing to install.
get_code_actions 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 get_code_actions 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 get_code_actions. 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.
get_code_actions is provided by the MCP-TY MCP server (qinsehm1128/mcp-ty). 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 →