gigaxity-deep-research

# Gigaxity Deep Research A skill-format reference for any agent (Claude Code, Codex, Cursor, Hermes, plain-MCP) calling this server. For human-readable installation instructions, see [README.md](README.md). For harness-agnostic routing logic and the pasteable instruction block (drop into your harness's global `CLAUDE.md` / `AGENTS.md` or a standalone agent's system prompt), see [CLAUDE.md](CLAUDE.md). ## Quick Start The MCP server exposes **six tools** — two primitives plus four deep-research tools. Pick one based on query type, call it, return the result to the user verbatim. ``` # Primitives — raw and combined behavior in one call search(query) # Multi-source aggregation, no LLM research(query) # Search + synthesis with citations, single call # Deep-research tools — discrete steps, drive each independently ask(query) # Fast conversational answer (direct LLM, no search) discover(query) # Exploratory expansion + gap detection synthesize(query, sources) # Citation-aware fusion of pre-gathered content reason(query, sources) # Synthesize + explicit chain-of-thought depth control ``` ## Workflow ### Phase 1: Classify the query ``` Query class? ├── "what is X right now / when was X / latest version" │ → Phase 2A (ask) │ ├── "tell me about X" (cold start, no prior context) │ → Phase 2B (discover → read → synthesize) │ ├── "compare X vs...