tavily-proxy

tavily-proxy

A Cloudflare Worker that proxies requests to the Tavily API with automatic key rotation from a pool, providing search, extract, crawl, and map tools via MCP.

Category
访问服务器

README

tavily-proxy

A Cloudflare Worker that acts as an MCP (Model Context Protocol) proxy for the Tavily API. It provides the same tools as the official Tavily MCP server, but with an API key pool — automatically rotating through multiple Tavily keys and selecting the one with the most remaining credit.

Features

  • MCP Server — Streamable HTTP transport at POST /mcp, compatible with any MCP client
  • 4 Tavily Tools — tavily-search, tavily-extract, tavily-crawl, tavily-map
  • API Key Pool — Multiple Tavily API keys stored in Cloudflare KV; each request picks the key with the highest remaining credit
  • Key Management API — HTTP endpoints to add/delete keys and query their status
  • Auth Protected — All endpoints (except health check) require an x-api-key header

Endpoints

Method Path Description
POST /mcp MCP Streamable HTTP endpoint (tool calls)
POST /api/keys Add a Tavily API key to the pool
DELETE /api/keys Remove a Tavily API key from the pool
GET /api/keys List all keys and their remaining credits
GET / Health check (no auth required)

All endpoints except GET / require the x-api-key header matching your configured AUTH_KEY.

Setup

Prerequisites

Local Development

# Install dependencies
npm install

# Set your auth key for local dev (already in .dev.vars)
# AUTH_KEY=test-secret-key

# Start local server
npm run dev

Wrangler simulates KV locally — no Cloudflare account needed for development.

Deploy to Production

  1. Create a KV namespace:

    npx wrangler kv namespace create KV
    
  2. Update wrangler.toml — replace YOUR_KV_NAMESPACE_ID with the real ID from step 1.

  3. Set the auth secret:

    npx wrangler secret put AUTH_KEY
    
  4. Deploy:

    npm run deploy
    
  5. Add Tavily API keys to the pool:

    curl -X POST https://your-worker.workers.dev/api/keys \
      -H "Content-Type: application/json" \
      -H "x-api-key: your-auth-key" \
      -d '{"apiKey": "tvly-xxx"}'
    

Usage

Connect MCP Clients

With mcp-remote (for clients like Cursor, Claude Desktop, etc.):

{
  "mcpServers": {
    "tavily-proxy": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://your-worker.workers.dev/mcp",
        "--header", "x-api-key:${AUTH_KEY}"
      ],
      "env": {
        "AUTH_KEY": "your-auth-key"
      }
    }
  }
}

Key Management

# Add a key (auto-queries remaining credit from Tavily)
curl -X POST https://your-worker.workers.dev/api/keys \
  -H "Content-Type: application/json" \
  -H "x-api-key: your-auth-key" \
  -d '{"apiKey": "tvly-xxx"}'

# List all keys and credits
curl https://your-worker.workers.dev/api/keys \
  -H "x-api-key: your-auth-key"

# Delete a key
curl -X DELETE https://your-worker.workers.dev/api/keys \
  -H "Content-Type: application/json" \
  -H "x-api-key: your-auth-key" \
  -d '{"apiKey": "tvly-xxx"}'

How the Key Pool Works

  1. When a tool is called, KV.list() retrieves all stored API keys
  2. The key with the largest remaining credit is selected
  3. The request is proxied to api.tavily.com using that key
  4. After the call, the estimated credit cost is deducted locally in KV
  5. When a key is added via /api/keys, its real remaining credit is fetched from Tavily's /usage endpoint

License

ISC

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选