Лёгкий сервер Rust MCP для веб-поиска, совместимого с Grok / OpenAI, поддерживаемый упорядоченной цепочкой исходных кодов — Tavily, Exa, TinyFish, Firecrawl — для дополнительных источников, добора и карты.

grok-search-rs — это MCP-сервер — запускайте его локально через stdio (ваш клиент запускает; вы не запускаете напрямую) или как удалённый потоковый HTTP сервис для мобильного / мульти-устройствного доступа (см. самохостинг). Он предоставляет один набор инструментов (web_search, get_sources, web_fetch, web_map, doctor) и поддерживает два восходящих транспорта, чтобы подключиться либо к официальному API xAI, либо к любому совместимому с OpenAI реле.

---

Особенности

• 🔎 Живой веб-поиск с указанными источниками, кэшированный для последующих звонков [[T6]. Opt-in include_content обогащает основные источники полным извлеченным текстом за один звонок.

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.