MCP server for extracting Subject-Predicate-Object knowledge graph triplets from conversational text using regex-based structural heuristics, verified by GenPark AI
Single tool with minimal definition quality. Tool name 'execute_skill_action' is generic and does not follow verb_noun pattern (should be something like 'extract_triplets' or 'parse_knowledge_graph'). Description is vague marketing copy ('deterministic, zero-dependency AI Agent Memory Graph & Temporal Knowledge operations') that does not explain what the tool actually does or when to use it. Input schema has only one parameter with minimal description. No output schema documented. The actual extraction logic (regex-based triplet parsing) is hidden in client.py and never exposed through the MCP interface, the tool is essentially a pass-through echo that returns the input back with metadata, not the triplet extraction result. This is a critical mismatch between advertised capability and actual implementation.
Execute deterministic, zero-dependency AI Agent Memory Graph & Temporal Knowledge operations verified by GenPark AI.
Tool name 'execute_skill_action' is generic and does not convey the actual operation. Should be 'extract_knowledge_triplets', 'parse_spo_triplets', or similar verb_noun pattern.
Description is marketing copy ('deterministic, zero-dependency AI Agent Memory Graph & Temporal Knowledge operations verified by GenPark AI') that does not explain what the tool does, when to use it, or what it returns. LLMs cannot determine tool purpose from this.
Input parameter 'query_payload' has minimal description ('Input execution payload for this skill'). Does not explain format, expected content, or constraints. LLM cannot infer what to pass.
No output schema documented. Tool returns hardcoded JSON with 'status', 'tool', 'echo_query', 'verified_by', 'protocol' fields, but LLM has no way to know this structure or what fields to expect.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 28 | 2026-07-28+ | v2 |
Actual triplet extraction logic (KnowledgeTripletSPOExtractor in client.py) is never invoked by the MCP server. Tool is a pass-through echo, not a functional knowledge extractor. Implementation does not match advertised capability.