MCP server for monitoring AI agent observability, telemetry, and performance metrics including token usage, tool error rates, and latency measurements
This server has critical definition failures. The single tool 'execute_skill_action' has no visible input schema, no parameter descriptions, and a vague 18-character description. The mcp_server.py file does not implement the MCP protocol, it merely prints a JSON status message and exits. There is no tool registration mechanism, no request/response handling, and no actual MCP server implementation. The tool definition is inferred from example_usage.py, not explicitly registered. This is a non-functional stub.
Execute observability and telemetry monitoring skill action for AI agents
No input schema visible. Tool has no declared parameters, types, or constraints.
Description is 18 characters ('Execute observability...'), below 20-char minimum. Lacks WHAT, WHEN, and WHY context for LLM selection.
No parameter descriptions. Tool accepts 'agent_session_logs' (inferred from client.py) but no schema or description exists. LLM cannot determine format, required fields, or constraints.
Output schema not documented. client.py returns a dict with 'total_token_usage', 'tool_error_rate_pct', 'latency_p95_ms' but no schema is declared. LLM cannot plan downstream use of these fields.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 15 | 2026-07-28+ | v2 |
Tool name 'execute_skill_action' is generic and vague. Does not start with a clear action verb (get, create, search, etc.). 'execute' + 'skill_action' is redundant and does not convey what the tool actually does (monitor telemetry).