"author:adeoluo" matching MCP servers:

Enables MCP clients to count tokens and estimate costs, run BM25 search, compare model evaluations with paired bootstrap and McNemar tests, validate JSON Schema output, and scan for prompt injection and PII.

Enables AI assistants to persist, version, retrieve, and consolidate episodic, semantic, and procedural knowledge in SQLite with hybrid search, then expose that long-term memory to MCP clients such as Claude Desktop or VS Code.