exa-websets-mcp

exa-websets-mcp

Unified gateway to Exa, Websets, and Deep Search for code search, deep research, and structured citations via any MCP client.

Category
访问服务器

README

What This Does

This MCP server acts as a unified gateway that lets you query Exa (for code search), Websets (for deep research), and Deep Search (for structured, citation-backed answers) through **any MCP client — including Poke AI, Cursor, and Windsurf.

It enables you to:

  • Search across custom collections of websites simultaneously (vs. searching one site at a time)
  • Find real-time information beyond training data (current news, market updates, new companies)
  • Access specialized databases like Crunchbase, Pitchbook, and LinkedIn for verified business information
  • Monitor specific industries or trends by searching relevant publications together
  • Verify contact information across multiple sources for accuracy
  • Compile comprehensive research reports by pulling from diverse authoritative sources
  • Conduct competitive analysis by gathering data across company websites, news sources, and business directories

Features

  • Unified Gateway: Access all tools through a single Render deployment
  • Code Search: Specialized Exa model for coding questions
  • Websets: Deep research and list management
  • Deep Search: Structured outputs with field-level citations and deep-reasoning support
  • Cloud Ready: Deploy to Render with one click
  • Universal Compatibility: Works with Poke, Cursor, Windsurf, and any standard MCP client

Capabilities Reference

What this MCP server allows you to do:

  • Search across custom collections of websites simultaneously (vs. searching one site at a time)
  • Find real-time information beyond training data (current news, market updates, new companies)
  • Access specialized databases like Crunchbase, Pitchbook, and LinkedIn for verified business information
  • Monitor specific industries or trends by searching relevant publications together
  • Verify contact information across multiple sources for accuracy
  • Compile comprehensive research reports by pulling from diverse authoritative sources
  • Conduct competitive analysis by gathering data across company websites, news sources, and business directories

Quick Start

Prerequisites

  • Exa API Key
  • An MCP Client (Poke, Cursor, Windsurf, etc.)
  • Render account (free tier works)

Option 1: Deploy to Render (Recommended)

  1. Fork this repository.
  2. Create a new Web Service on Render.
  3. Connect your forked repository.
  4. Set environment variables:
    • EXA_API_KEY: Your Exa API key
    • PORT: 8080 (optional, Render sets this automatically)
  5. Get your MCP URL: https://your-service-name.onrender.com

Option 2: Run Locally

  1. Clone the repository:
    git clone https://github.com/kabirrgrover/exa-websets-mcp.git
    cd exa-websets-mcp
    
  2. Install dependencies:
    npm install
    
  3. Configure environment: Set EXA_API_KEY in your environment.
  4. Run the server:
    npm start
    
    Server runs at: http://localhost:8080

Client Configuration

To connect this server, use the URLs below. These work with any MCP-compliant client.

1. Websets (Research)

  • URL: https://your-service-name.onrender.com/websets/sse
  • Use for: Research, Lead Gen, Lists

2. Exa (Coding)

  • URL: https://your-service-name.onrender.com/mcp
  • Use for: Coding questions, Documentation search

3. Deep Search (Structured Answers)

  • URL: https://your-service-name.onrender.com/deep/sse
  • Use for: Structured outputs with citations, deep-reasoning queries

Example MCP Client Config

{
  "mcpServers": {
    "exa-research": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://your-app.onrender.com/websets/sse"]
    },
    "exa-code": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://your-app.onrender.com/mcp"]
    },
    "exa-deep": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://your-app.onrender.com/deep/sse"]
    }
  }
}

Troubleshooting

"Invalid MCP server URL"

  • Verify your URL matches the endpoints above exactly.
  • Ensure the server is live on Render (green status).

"Authentication failed"

  • Verify EXA_API_KEY is set correctly in Render environment variables.

Messages failing

  • If Poke cannot send messages, ensure you are using the correct endpoint (/websets/sse for Websets).

Architecture

MCP Client <-> Gateway (Express) <-> [Exa MCP, Websets MCP, Deep Search MCP]

License

MIT License

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