search-boost-mcp
A multi-engine web search MCP server that integrates with coding agents, offering parallel search, page fetching, X/Twitter search, deep research, and configurable free/API layers.
README
search-boost-mcp
Multi-engine web search MCP server for coding agents. One CLI install wires it into Cursor, Cursor CLI, Codex, Claude Code, Grok Build, and Antigravity.
search-boost family
Project For Link search-boost-mcp (this repo) Cursor · Codex · Claude · Grok · Antigravity via MCP you are here dsh-search-boost DeepSeek Harness bundle plugin GitHub · npm pi-search-boost pi extension GitHub · npm
Search engines come from dsh-search-boost (bundled as an npm dependency): on the free layer, Bing, Exa-free, Google News, and Yahoo run in parallel; the api layer adds DuckDuckGo, Antigravity CLI (when available), and keyed Tavily / Brave / Exa. Also included: X/Twitter fallback, Jina page fetch, and deep-research rounds.
中文文档 → README_zh.md
What's new in v0.1.2
- Free-layer engine pool rebuilt after live benchmarks: Bing + Exa-free + Google News + Yahoo for general search; DuckDuckGo kept for domain-restricted routes (e.g.
x_searchfallback withsite:queries). x_searchfallback auto-prependssite:x.comfor multi-engine domain search so keyword mode works without XAI credentials.- Depends on
dsh-search-boost@0.1.2.
Install (recommended)
Requires Node ≥ 22.13.
npm install -g search-boost-mcp
search-boost setup # interactive: keys → layer → agents
# or non-interactive:
search-boost install -y # all detected agents
Restart each agent after install so MCP reloads.
One-liners by agent
search-boost install -t cursor -y
search-boost install -t codex,claude -y --auto-allow
search-boost install -t grok -y --auto-allow
search-boost install -t antigravity --workspace --auto-allow -y
Preview without writing: search-boost install --dry-run -y
What you get
| MCP tool | Purpose |
|---|---|
fused_search |
Multi-engine parallel search, dedupe, cross-ranking |
fetch_page |
Full page text (Jina + HTML fallback, optional focus) |
x_search |
X/Twitter keyword / user / thread |
deep_research |
One research round — gaps + suggested follow-ups |
search_layer |
Show or set free (keyless) vs api (keyed engines) |
search_stats |
Cache hits, engine availability, diagnostics |
Also: resource search-boost://policy · prompt search_routing
Layers
- free — Bing + Exa-free + Google News + Yahoo; no API keys. DuckDuckGo is used only for domain-restricted searches (e.g.
x_searchfallback). - api — free-layer engines plus DuckDuckGo, Antigravity CLI (when available), and Tavily / Brave / Exa when keys are set
Keys: search-boost config keys → ~/.dsh-search-boost-keys.json (or env TAVILY_API_KEY, BRAVE_API_KEY, EXA_API_KEY).
CLI cheat sheet
| Command | What it does |
|---|---|
search-boost |
Interactive TUI |
search-boost setup |
Onboarding (keys + layer + install) |
search-boost install / uninstall |
Wire MCP + prompts into agents |
search-boost serve |
Run MCP stdio server (used by agents) |
search-boost status |
Keys, layer, per-agent configured state |
search-boost config keys|layer|search |
Keys, default layer, native-search replace |
search-boost print <agent> |
Print MCP snippet without writing |
search-boost agents |
Machine-readable agent list |
Install flags: -t cursor,codex,…|auto|all · -y (non-interactive) · --dry-run · --auto-allow · --replace-native / --keep-native · --scope user|project (Grok) · --workspace (Antigravity .agents/)
Supported agents
| Agent | MCP config | Also installs |
|---|---|---|
| Cursor IDE / CLI | ~/.cursor/mcp.json |
hook, skill, optional CLI auto-allow |
| Codex CLI | ~/.codex/config.toml |
AGENTS.md, skill |
| Claude Code | ~/.claude.json |
CLAUDE.md, skill, permissions |
| Grok Build | ~/.grok/config.toml |
rule, skill · grok-plugin |
| Antigravity | ~/.gemini/config/mcp_config.json |
AGENTS.md, GEMINI.md, skill, optional workspace |
Prompts use model-discretion wording (search when you choose — not forced every turn). See agents/ for per-agent templates.
Native web search: Codex web_search and Claude WebSearch can be disabled with --replace-native (default on -y). Cursor / Antigravity rely on skill + hook preference only. Grok native browse is left on.
Grok plugin
grok plugin install ./grok-plugin --trust
search-boost install -t grok -y --auto-allow
Details → grok-plugin/README.md
Development
git clone https://github.com/Mr-remon219/search-boost-mcp.git
cd search-boost-mcp && npm install
npm run check && npm run test:install && npm run smoke
node cli.mjs install --dry-run -y
Local clone installs write node /path/to/cli.mjs serve (not npx). Sibling checkout: set SEARCH_BOOST_DSH_ROOT=../dsh-search-boost if needed.
License
MIT
Links: Issues · dsh-search-boost · pi-search-boost
Friendly link: LINUX DO 社区
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。