MCP server for code refactoring and linting capabilities
The GenPark AI Code Refactoring Lint Fixer server has severe definition quality issues. The single tool 'execute_skill_action' is barely defined in the source code. The mcp_server.py file contains only a stub that prints a JSON status message, it does not actually register tools with the MCP protocol, define schemas, or implement the Model Context Protocol correctly. The tool name is vague (violates verb_noun pattern), no description is visible, no input/output schemas are defined, and no error handling is present. This is a non-functional skeleton, not a production-ready MCP server.
Tool name 'execute_skill_action' is vague and does not follow verb_noun pattern. 'execute' is overly generic; should be 'refactor_code' or 'apply_lint_fixes' to convey the actual action.
No tool description visible in source code. LLMs cannot determine when or why to select this tool without a description.
No input schema defined or visible. Tool parameters are not specified, making it impossible for clients to invoke the tool correctly.
No output schema documented. Callers do not know what fields to expect in the response.
mcp_server.py does not implement the MCP protocol. It only prints a static JSON message and exits. No message handling, no tool invocation, no proper JSON-RPC or streaming communication.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 11 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If the tool fails, there is no mechanism to report errors or guide the LLM to retry or select an alternative.
No security validation. Tool accepts arbitrary code as input with no sanitization or permission checks.