tavily-search-mcp
A cost-aware stdio MCP server for the Tavily Search API, supporting basic, fast, ultra fast, and advanced searches with credit tracking and automatic API key rotation.
README
Tavily Search MCP
A cost-aware stdio MCP server for the official Tavily Search API.
Tool
tavily_search supports:
- Basic, Fast, and Ultra Fast Search at 1 API credit.
- Advanced Search at 2 API credits, only when explicitly selected.
- General, news, and finance topics.
- Domain and date filters.
- Up to 20 ranked results with source URLs and relevance scores.
- Reported credit usage, response time, and request ID.
The server always sends auto_parameters: false, include_usage: true, and excludes generated answers, raw pages, and images. This keeps cost and response size predictable while leaving synthesis to the MCP client.
Configuration
Required at call time:
TAVILY_API_KEY
On Windows, run npm run setup for the first-install configuration window. Enter multiple API keys separated by semicolons. It saves the API URL as a non-secret setting and stores the key array as a current-user DPAPI ciphertext under %APPDATA%\tavily-search-mcp\api-key.dpapi. Environment variables (TAVILY_API_KEYS or TAVILY_API_KEY) still take precedence for CI or temporary sessions.
Requests rotate across configured keys. Authentication, rate-limit, and quota responses (401, 429, 432, 433) can switch to the next distinct key, with a hard maximum of three attempts per MCP call. Server failures and ambiguous errors are not retried.
Optional:
TAVILY_API_URL=https://api.tavily.com/search
The server starts and lists tools without a key, then fails closed with a clear error if a search is attempted before TAVILY_API_KEY is configured. Secrets are never accepted as tool arguments or printed.
Each installation must use its own Tavily credentials. Do not share .env files, DPAPI ciphertext, setup screenshots, or API keys with other users.
Development
npm install
npm run check
Codex configuration
After building, register the compiled entry point and forward only the required environment variable:
[mcp_servers.tavily_search]
command = "node"
args = ["D:/path/to/tavily-search-mcp/dist/index.js"]
env_vars = ["TAVILY_API_KEYS", "TAVILY_API_KEY", "TAVILY_API_URL"]
startup_timeout_sec = 20
tool_timeout_sec = 60
No request is retried automatically. HTTP redirects are rejected so the API key cannot be forwarded to another origin.
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。