Grok / OpenAI 호환 웹 검색용 경량 Rust MCP 서버로, 보조 소스, fetch, map을 위한 순서화된 소스 체인 — Tavily, Exa, TinyFish, Firecrawl — 로 뒷받침됩니다.

grok-search-rs는 MCP 서버 — stdio를 통해 로컬에서 실행하며(클라이언트가 직접 실행하지 않음) 또는 원격 스트리밍 가능한 HTTP 서비스로 모바일/다중 장치 접근을 위한 서비스(셀프 호스팅 참조)로 운영됩니다. 이 서버는 한 세트의 도구 세트(web_search, get_sources, web_fetch, web_map, doctor)를 제공하며, xAI 공식 API나 OpenAI 호환 릴레이에 연결할 수 있도록 두 개의 업스트림 전송을 지원합니다.

---

특징

• 🔎 인용된 출처가 포함된 실시간 웹 검색, 후속 get_sources 통화를 위해 캐시됨. 옵트인 include_content는 상위 출처를 한 통화에서 전체 텍스트 추출로 풍부하게 합니다.

GrokSearch-rs

A lightweight Rust MCP server for Grok / OpenAI‑compatible web search, backed by an ordered source chain — Tavily, Exa, TinyFish, Firecrawl — for supplemental sources, fetch, and map.

grok-search-rs is an MCP server — run it locally over stdio (your client launches it; you do not run it directly) or as a remote Streamable HTTP service for mobile / multi‑device access (see self-hosting). It exposes one set of tools (web_search, get_sources, web_fetch, web_map, doctor) and supports two upstream transports so you can plug into either xAI’s official API or any OpenAI‑compatible relay.

---

Features

• 🔎 Live web search with cited sources, cached for follow‑up get_sources calls. Opt‑in include_content enriches the top sources with full extracted text in one call.
• 📏 Response budgeting — web_search keeps responses inside agent context limits: only the top max_inline_sources carry inline text, a whole‑response char budget (response_max_chars, default 45k — sized to stay under the MCP client token ceiling after JSON serialization) trims tail sources with recovery notes, response_format: "concise" | "detailed" picks the payload size, and get_sources pages through cached sources with offset/limit. The session cache always keeps full content.
• 🧩 Structured web_fetch — GitHub issues/PRs/releases, StackExchange/MathOverflow, arXiv, and Wikipedia URLs are parsed by specialist extractors into clean Markdown (title, state/labels, release notes, accepted‑answer ordering, abstracts, vote‑sorted answers). Specialist extractors need no API key. Anything else falls back to the generic source chain (Tavily → Exa → TinyFish → Firecrawl, as configured) — so with no source provider configured, ordinary URLs cannot be fetched at all, only the specialist families above. Output carries source_type and a fallback_reason when a specialist was skipped.
• 🔀 Two transports — native xAI Responses (/v1/responses) or any OpenAI‑compatible chat‑completions gateway (/v1/chat/completions). Pick by env vars; no flag.
• 🔐 Optional Grok OAuth mode — login/status/logout commands store a local xAI OAuth token for Responses auth, so the MCP server can run without GROK_SEARCH_API_KEY.
• 🌐 Optional remote mode — build with --features http to serve the same tools over Streamable HTTP (multi‑tenant, bring‑your‑own‑key via request headers) for mobile / multi‑device access. See self-hosting.