Skip to main content
Glama
grok-native-search-mcp

grok-native-search-mcp

by zuozh11

Grok Native Search MCP

ミニマルな stdio MCP Server で、3つの読み取り専用ツールを提供します:

  • web_search(query):Grok ネイティブ Web Search

  • x_search(query):Grok ネイティブ X Search

  • web_fetch(url):Jina Reader で Web ページを Markdown に変換

検索は固定で grok-4.6、reasoning.effort: low、max_turns: 1 を使用します。1ターン内で補完的な検索の並行実行を許可し、十分な一次証拠が見つかった時点で停止し、証拠が不足または矛盾する場合のみ範囲を拡大します。ツールの応答は解析や書き換えを行わず、そのまま MCP テキストとして返します。

ツールのルーティング:既知の URL またはページ本文の検証が必要な場合は web_fetch を使用;X の投稿、アカウント、スレッド、トレンドには x_search を使用;明確な URL がないその他の全 Web 検索には web_search を使用します。検索で検証が必要な外部 URL が得られた場合は、引き続き web_fetch を呼び出します。

環境変数

変数

用途

XAI_API_KEY

xAI または互換ゲートウェイの API Key

XAI_BASE_URL

オプション、Responses API のベースアドレス;デフォルトは https://aiapiv2.kamipon.com:442/v1 を使用

JINA_API_KEY

Jina Reader API Key

HTTP_PROXY / HTTPS_PROXY / NO_PROXY

オプション、Jina Reader リクエストのみに使用する環境プロキシ設定

Related MCP server: Ollama Web Search

npx での起動

npx -y grok-native-search-mcp@latest

Codex 設定

[mcp_servers.grok_native_search]
command = "npx"
args = ["-y", "grok-native-search-mcp@latest"]
env_vars = ["XAI_API_KEY", "JINA_API_KEY", "HTTP_PROXY", "HTTPS_PROXY", "NO_PROXY"]

設定後、Codex を再起動します。

ローカル開発

npm install
npm test

Available Tools

3 tools
web_fetchA
Read-only

Use this when an exact HTTP(S) URL is known, including URLs returned by web_search or x_search, and the task is to read, quote, summarize, or verify page text. Prefer it over Browser, curl, or shell when no login, click, form interaction, or visual inspection is required. Do not use it to discover URLs. Returns raw Markdown from Jina Reader.

Inputs: url (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: web_search for general web discovery, x_search specifically for X content, and web_fetch for retrieving a known URL. The descriptions explicitly cross-reference each other (e.g., web_search notes 'For X-only content use x_search'), leaving no ambiguity about which tool to select.

    Naming Consistency5/5

    All three tool names follow a consistent `[source]_[action]` pattern: web_search, x_search, web_fetch. The naming convention is uniform, predictable, and immediately conveys scope (web vs. x) and operation (search vs. fetch).

    Tool Count5/5

    With only 3 tools, the server is tightly scoped for its purpose: general web search, X-specific search, and URL fetching. This is well within the ideal 3–15 range and every tool earns its place; adding more would likely introduce redundancy.

    Completeness5/5

    The surface covers the full lifecycle of a search task: discover sources (web_search, x_search) and then retrieve/verify content (web_fetch). The tools explicitly reference each other to create a complete workflow, with no obvious gaps for the stated domain.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables real-time web search via DeepSeek's search-enhanced dialogue, providing search results as answers through MCP tools.
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables web search and web fetch operations using Ollama's hosted APIs, allowing MCP clients to search the web and retrieve page content.
      2
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables web search, page fetching and cleaning, OCR from images, and broken-link checking through MCP tools, with multi-provider aggregation, caching, and anti-detection features.
      35 npm
      MIT