Midas
Local-first, source-traceable agent memory — no LLM at ingest, fully offline
Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
MIDAS_MCP_DBPath to a SQLite file to persist memory across restarts (default: in-memory)
MIDAS_MCP_EMBEDDEREmbedding backend: 'local' (bge ONNX, offline) or 'hashing' (default: local)
MIDAS_MCP_MAX_RECORDSCap the store; above it the lowest-value memories are auto-forgotten (no LLM)
MIDAS_MCP_MIN_IMPORTANCERelevance floor 1-5 for auto-capture; turns scoring below it are skipped
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Public MCP server for the LLM Search Engine
Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines.