Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
Provider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
AGENT_WEB_SEARCH_PROVIDERS, ARK_API_KEY, GEMINI_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY, AGENT_WEB_SEARCH_RESPONSES_API_KEY, AGENT_WEB_SEARCH_RESPONSES_BASE_URL, AGENT_WEB_SEARCH_MESSAGES_API_KEY, AGENT_WEB_SEARCH_MESSAGES_BASE_URL, TAVILY_API_KEY, BRAVE_SEARCH_API_KEY, PERPLEXITY_API_KEY, YDC_API_KEY, EXA_API_KEY, PARALLEL_API_KEY, ZHIPU_WEB_SEARCH_API_KEY, ZHIPU_CHAT_SEARCH_API_KEY「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"agent-web-search": {
"command": "uvx",
"args": [
"agent-web-search-mcp"
],
"env": {
"AGENT_WEB_SEARCH_PROVIDERS": "your-value",
"ARK_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"XAI_API_KEY": "your-value",
"DEEPSEEK_API_KEY": "your-value",
"AGENT_WEB_SEARCH_RESPONSES_API_KEY": "your-value",
"AGENT_WEB_SEARCH_RESPONSES_BASE_URL": "your-value",
"AGENT_WEB_SEARCH_MESSAGES_API_KEY": "your-value",
"AGENT_WEB_SEARCH_MESSAGES_BASE_URL": "your-value",
"TAVILY_API_KEY": "your-value",
"BRAVE_SEARCH_API_KEY": "your-value",
"PERPLEXITY_API_KEY": "your-value",
"YDC_API_KEY": "your-value",
"EXA_API_KEY": "your-value",
"PARALLEL_API_KEY": "your-value",
"ZHIPU_WEB_SEARCH_API_KEY": "your-value",
"ZHIPU_CHAT_SEARCH_API_KEY": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add agent-web-search --env AGENT_WEB_SEARCH_PROVIDERS=your-value --env ARK_API_KEY=your-value --env GEMINI_API_KEY=your-value --env XAI_API_KEY=your-value --env DEEPSEEK_API_KEY=your-value --env AGENT_WEB_SEARCH_RESPONSES_API_KEY=your-value --env AGENT_WEB_SEARCH_RESPONSES_BASE_URL=your-value --env AGENT_WEB_SEARCH_MESSAGES_API_KEY=your-value --env AGENT_WEB_SEARCH_MESSAGES_BASE_URL=your-value --env TAVILY_API_KEY=your-value --env BRAVE_SEARCH_API_KEY=your-value --env PERPLEXITY_API_KEY=your-value --env YDC_API_KEY=your-value --env EXA_API_KEY=your-value --env PARALLEL_API_KEY=your-value --env ZHIPU_WEB_SEARCH_API_KEY=your-value --env ZHIPU_CHAT_SEARCH_API_KEY=your-value -- uvx agent-web-search-mcp動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"agent-web-search": {
"command": "uvx",
"args": [
"agent-web-search-mcp"
],
"env": {
"AGENT_WEB_SEARCH_PROVIDERS": "your-value",
"ARK_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"XAI_API_KEY": "your-value",
"DEEPSEEK_API_KEY": "your-value",
"AGENT_WEB_SEARCH_RESPONSES_API_KEY": "your-value",
"AGENT_WEB_SEARCH_RESPONSES_BASE_URL": "your-value",
"AGENT_WEB_SEARCH_MESSAGES_API_KEY": "your-value",
"AGENT_WEB_SEARCH_MESSAGES_BASE_URL": "your-value",
"TAVILY_API_KEY": "your-value",
"BRAVE_SEARCH_API_KEY": "your-value",
"PERPLEXITY_API_KEY": "your-value",
"YDC_API_KEY": "your-value",
"EXA_API_KEY": "your-value",
"PARALLEL_API_KEY": "your-value",
"ZHIPU_WEB_SEARCH_API_KEY": "your-value",
"ZHIPU_CHAT_SEARCH_API_KEY": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"agent-web-search": {
"type": "stdio",
"command": "uvx",
"args": [
"agent-web-search-mcp"
],
"env": {
"AGENT_WEB_SEARCH_PROVIDERS": "your-value",
"ARK_API_KEY": "your-value",
"GEMINI_API_KEY": "your-value",
"XAI_API_KEY": "your-value",
"DEEPSEEK_API_KEY": "your-value",
"AGENT_WEB_SEARCH_RESPONSES_API_KEY": "your-value",
"AGENT_WEB_SEARCH_RESPONSES_BASE_URL": "your-value",
"AGENT_WEB_SEARCH_MESSAGES_API_KEY": "your-value",
"AGENT_WEB_SEARCH_MESSAGES_BASE_URL": "your-value",
"TAVILY_API_KEY": "your-value",
"BRAVE_SEARCH_API_KEY": "your-value",
"PERPLEXITY_API_KEY": "your-value",
"YDC_API_KEY": "your-value",
"EXA_API_KEY": "your-value",
"PARALLEL_API_KEY": "your-value",
"ZHIPU_WEB_SEARCH_API_KEY": "your-value",
"ZHIPU_CHAT_SEARCH_API_KEY": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
AGENT_WEB_SEARCH_PROVIDERS envAGENT_WEB_SEARCH_RESPONSES_BASE_URL envAGENT_WEB_SEARCH_MESSAGES_BASE_URL envこの設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント JerryLiu369 で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:ARK_API_KEY, GEMINI_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY, AGENT_WEB_SEARCH_RESPONSES_API_KEY, AGENT_WEB_SEARCH_MESSAGES_API_KEY, TAVILY_API_KEY, BRAVE_SEARCH_API_KEY, PERPLEXITY_API_KEY, YDC_API_KEY, EXA_API_KEY, PARALLEL_API_KEY, ZHIPU_WEB_SEARCH_API_KEY, ZHIPU_CHAT_SEARCH_API_KEY
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.8.1)がレジストリに届いたのは15 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Context7, Codebase Memory, Exa
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Agent-native web search — model-native grounding and agent search APIs behind one provider-neutral contract.
English | 简体中文
One-click remote MCP
Works with Codex CLI, Claude Code, OpenCode, Hermes, DeepSeek Harness (DSH), ordinary shell scripts, Python applications, and remote Streamable HTTP MCP clients.
Quickstart · Use with an agent · Providers · Configuration
Shared interface · Other interfaces · Troubleshooting · FAQ · Architecture · Development
Agent Web Search (PyPI: agent-web-search-mcp) is an open-source, MIT-licensed web search MCP server, CLI, and Python library for AI agents. It gives an agent three ways to reach the same provider-neutral search core: a native MCP tool, a native plugin (Hermes, DeepSeek Harness), or a CLI taught through a standard Agent Skill.
If you are an AI agent: install with
pipx install agent-web-search-mcp
(or try instantly with
uvx --from agent-web-search-mcp agent-web-search " "),
then read
skills/agent-web-search/SKILL.md—
it teaches the CLI pathway only (for MCP setups, follow Option 1
instead).
llms.txt
is the machine-readable doc index.
This is not a Google/Bing/Baidu metasearch wrapper. Traditional search aggregation fans a keyword query out to conventional engines and merges their result pages. Agent Web Search instead aggregates search capabilities built for agents: model-native web grounding, agent-oriented search APIs, and context-ready sources that accept natural-language questions and return answers, citations, or structured evidence in forms an agent can use directly. DDGS is the only conventional search backend in the current provider set.
Natural-language question
| v SearchEngine +-----------+-----------+ | | | v v v DDGS Model Agent grounding APIs (Responses, (Exa, ARK, Grok, Parallel, Gemini...) Tavily...)
Three steps, about a minute: try it instantly, install it once, then connect your agent. Requirements: Python 3.10+. Default providers (DDGS, Exa, Parallel) require no API key.
Test immediate search capabilities using uvx (no environment modification):
# Direct natural-language search with keyless defaults
uvx --from agent-web-search-mcp agent-web-search "What changed in the latest OpenAI Codex CLI?"
uvx agent-web-search-mcp --help
Install once into your global user environment (recommended):
# Recommended isolated installation
pipx install agent-web-search-mcp
python -m pip install agent-web-search-mcp
# 1. Verify the CLI and run a real search
agent-web-search --version agent-web-search "What changed in the latest OpenAI Codex CLI?"
agent-web-search-mcp --help
Two commands, two roles:
-
agent-web-search: Direct search CLI for terminals, shell scripts, and Agent Skills.
-
agent-web-search-mcp: Stdio and Streamable HTTP MCP server for MCP clients.
| Integration | Client / Environment | Setup |
|---|---|---|
| CLI + Skill *(Recommended)* | Terminal agents (Claude Code, Codex, OpenCode, Hermes) | npx skills add JerryLiu369/agent-web-search --skill agent-web-search (Details) |
| MCP (Stdio) | Codex CLI, Claude Code, Cursor, Cline, Roo Code | codex mcp add agent-web-search -- agent-web-search-mcp (Details) |
| DSH Plugin | DeepSeek Harness (desktop & web) | dsh plugin --profile desktop add github:JerryLiu369/agent-web-search (Details) |
| Hermes Plugin | Hermes Agent | hermes plugins install JerryLiu369/agent-web-search (Details) |
[!TIP]
Why CLI + Skill is recommended for shell-capable agents: If your agent already has terminal/bash execution capabilities (like Claude Code, Codex CLI, OpenCode, or Hermes), the CLI + Skill pathway offers the lowest friction and highest reliability. No MCP JSON configuration to debug, no background transport lifecycle to manage, and clean stdout JSON output taught through a standard Skill.
Traditional search aggregation (Google/Bing/Baidu wrappers, scraped SERPs) sends a keyword query to conventional engines and merges result pages. Agent Web Search instead aggregates search capabilities built for agents: one tool call returns structured, citation-ready evidence — or, through model-native grounding providers, a synthesized answer with explicit citations. A measured benchmark shows the practical difference: on a natural-language Chinese query asking for official sources, conventional SERP backends returned no government-domain results in the top 5, while the grounding provider returned official figures from China's General Administration of Customs with a working citation.
results; model-backed providers may also return an answer.The provider list is intentionally split by the kind of search capability it provides. Only DDGS is a conventional search backend; the other two groups are built around model-native grounding or agent-facing search services.
Free, keyless defaults: DDGS, Exa, and Parallel all work without an API
key. Exa and Parallel automatically use their free MCP transports until a
paid API key is provided.
| Provider | Website | Search backend | API key | Enabled by default |
|---|---|---|---|---|
| DDGS | DuckDuckGo | Conventional DuckDuckGo search | Free · no key required | Yes |
These providers use a model-native search or grounding surface. Their responses can include a model-generated answer together with citations or other explicit search evidence.
| Provider | Website | Model-native search surface | API key | Enabled by default |
|---|---|---|---|---|
| ARK | Volcengine Ark | Responses API with Doubao web-search grounding | ARK_API_KEY | No |
| Codex Alpha (experimental) | Alpha Search-compatible gateway | Model-backed Alpha Search surface | AGENT_WEB_SEARCH_CODEX_ALPHA_API_KEY | No |
| DeepSeek | DeepSeek API | Anthropic Messages API with native web search | DEEPSEEK_API_KEY | No |
| Gemini | Google AI | Gemini Google Search grounding | GEMINI_API_KEY | No |
| Grok | xAI | xAI web search and X Search | XAI_API_KEY | No |
| Responses | Responses API-compatible gateway | Generic OpenAI Responses API with web search grounding | AGENT_WEB_SEARCH_RESPONSES_API_KEY | No |
| Messages | Messages API-compatible gateway | Generic Anthropic Messages API with web search grounding | AGENT_WEB_SEARCH_MESSAGES_API_KEY | No |
| Zhipu Chat Search | Zhipu AI | GLM Chat Completions with native web search | ZHIPU_CHAT_SEARCH_API_KEY | No |
These providers expose search services for agent consumption: natural-language queries, structured source rows, high-signal excerpts, or citation-friendly metadata rather than a conventional search-page experience.
| Provider | Website | Agent-facing search surface | API key | Enabled by default |
|---|---|---|---|---|
| Exa | Exa | Semantic Search API or free MCP fallback | Free without key · optional EXA_API_KEY | Yes |
| Parallel | Parallel | Context-oriented search API or free MCP | Free without key · optional PARALLEL_API_KEY | Yes |
| Brave | Brave Search | Structured Web Search API | BRAVE_SEARCH_API_KEY | No |
| Perplexity | Perplexity API | Native structured Search API | PERPLEXITY_API_KEY | No |
| Tavily | Tavily | Agent-oriented Search API | TAVILY_API_KEY | No |
| You.com | You.com API | Unified web and news Search API | YDC_API_KEY | No |
| **Zhipu Web Sear
冒頭だけを表示しています。続きはリポジトリで読めます