Loading ToolBench
MCP server for recording desktop UI actions and generating executable macro scripts
This server has critical definition failures. The single tool 'execute_skill_action' has no visible input schema, no parameter descriptions, and a trivial 56-character description that does not explain WHAT the tool does, WHEN to use it, or what it returns. The mcp_server.py file contains only a stub that prints JSON and exits, it does not implement the MCP protocol at all. No tool registration with schemas is visible. The client.py and example_usage.py files show a Python class, not an MCP server. This is not a functional MCP server.
Execute a skill action for desktop UI automation
Tool description is 56 characters ('Execute a skill action for desktop UI automation'). Does not explain WHAT it does, WHEN to use it, or what it returns.
mcp_server.py is a non-functional stub. It prints JSON once and exits. Does not implement MCP protocol message handling (no stdin/stdout loop, no tool invocation dispatch, no response formatting).
No parameter descriptions. The tool accepts parameters (implied by client.py: event_stream_json, target_app) but none are documented. LLMs cannot infer parameter meaning from names alone.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 16 | 2026-07-28+ | v2 |
No output schema documented. Clients cannot know what fields to expect from the tool response. The example shows macro_script_python, action_count, replay_ready, but this is not formally declared.