A local-first, LLM-agnostic MCP server that lets you ask hard questions about your documents, media, and code, and get traceable answers entirely offline.
Local-first MCP server that turns project documentation and source code into durable, evidence-backed context for AI agents, with bounded retrieval and explicit gap reporting.
A lightweight, dependency-free MCP server that answers cited queries over a Tero corpus index.json via stdio JSON-RPC 2.0, with honest refusal semantics and no silent empty results.
Retrieval-only MCP server that turns any knowledge source (Obsidian vault, notes, reference sets) into searchable Qdrant-backed skills, exposing list_skills, search_vault, and search_skill tools for agents to query via stdio or SSE.