tavily-mcp-proxy
A proxy MCP server for Tavily search and extract APIs with support for multiple API keys, random rotation, and bearer token authentication.
README
tavily-mcp-proxy
Tavily MCP Proxy - Search via Tavily MCP with multiple keys, randomly selecting one each time.
通过 Tavily MCP 进行搜索,支持配置多个 API Key,每次调用随机选取一个。
Features / 功能
- 🐳 Docker-deployable Streamable HTTP MCP server / 支持 Docker 部署的 Streamable HTTP MCP 服务
- 🔑 Multiple Tavily API keys with random rotation / 多 Tavily API Key 随机轮换
- 🔒 Bearer token authentication for access control / Bearer Token 访问认证
- 🔍
tavily_searchandtavily_extracttools / 包含tavily_search和tavily_extract两个工具
Quick Start / 快速开始
git clone https://github.com/welyfun/tavily-mcp-proxy.git
cd tavily-mcp-proxy
Create a .env file or configure environment variables / 创建 .env 文件或配置环境变量
TAVILY_API_KEYS=tvly-xxx,tvly-yyy,tvly-zzz
ACCESS_KEYS=my-secret-key
PORT=3000
Generate a secure access key / 生成一个安全的访问密钥:
python3 generate-key.py
Docker
docker compose up -d
Local Dev / 本地开发
npm install
npm run dev
Configuration / 配置项
| Variable | Required | Description |
|---|---|---|
TAVILY_API_KEYS |
Yes | Tavily API keys, comma-separated / Tavily API Key,逗号分隔 |
ACCESS_KEYS |
No | Access keys for authentication, comma-separated. Omit to disable auth / 访问密钥,逗号分隔。留空则不校验 |
PORT |
No | Server port, default 3000 / 服务端口,默认 3000 |
Tools / 工具
tavily_search
Search the web using Tavily Search API. The query is forwarded with max_results fixed at 10. Metadata fields (response_time, usage, request_id, etc.) are stripped from the response.
使用 Tavily Search API 搜索网页。max_results 固定为 10,响应中已剔除元数据字段。
| Parameter | Type | Required | Description |
|---|---|---|---|
query |
string | Yes | Search query / 搜索关键词 |
tavily_extract
Extract web page content from one or more URLs using Tavily Extract API. Metadata fields are stripped from the response.
使用 Tavily Extract API 提取网页内容。响应中已剔除元数据字段。
| Parameter | Type | Required | Description |
|---|---|---|---|
urls |
string | string[] | Yes | URL(s) to extract / 要提取的 URL |
Client Configuration / 客户端配置
Claude Desktop
{
"mcpServers": {
"tavily": {
"url": "http://localhost:3000/mcp",
"headers": {
"Authorization": "Bearer my-secret-key"
}
}
}
}
Codex
[mcp_servers.tavily]
url = "http://localhost:3000/mcp"
http_headers = { "Authorization" = "Bearer my-secret-key" }
default_tools_approval_mode = "approve"
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.