mcp-web-search-server

Standalone MCP server exposing web_search and web_fetch tools over HTTP. Any MCP client (Claude Desktop, Cursor, etc.) can connect to it to perform web searches and fetch web pages.

Works out of the box with no API keys: web_search/web_search_exa use Exa's public MCP endpoint, which accepts unauthenticated (rate-limited) requests. Set EXA_API_KEY for higher limits, or PARALLEL_API_KEY to also enable web_search_parallel.

Tools

How it works:

┌──────────────┐     MCP HTTP      ┌──────────────────────────┐     HTTP      ┌──────────────┐
│  MCP Client   │ ◄───────────────► │  web-search-server        │ ◄──────────► │  Exa AI      │
│  (Claude,     │     Streamable    │  :9877/mcp               │               │  mcp.exa.ai  │
│   Cursor,     │                   │                          │               └──────────────┘
│   etc.)       │                   │  Tools:                  │
└──────────────┘                   │  • web_search (auto)     │ ── HTTP ──► ┌──────────────┐
                                   │  • web_search_exa        │               │  Parallel    │
                                   │  • web_search_parallel   │               │  search.     │
                                   │  • web_fetch             │               │  parallel.ai │
                                   └──────────────────────────┘               └──────────────┘

Key design decisions:

1. Plain async/await — no framework, just native fetch (Bun's fetch)

2. Streamable HTTP transport — uses WebStandardStreamableHTTPServerTransport from @modelcontextprotocol/sdk, with one session (transport + server instance) per connecting client

3. Provider selection — hash of session ID picks exa/parallel for the generic web_search tool, with env var overrides

4. HTML→Markdown — uses turndown for markdown extraction, a small state-machine for plain text extraction

Related MCP server: websearch-mcp-server

Quick Start

# Install dependencies
bun install

# Run the server (default port 9877)
bun run src/index.ts

Configuration

Environment variables:

Connect from an MCP client

Point your MCP client to: http://localhost:9877/mcp

This is a standard MCP server using the Streamable HTTP transport.

Usage Examples

Fetch a webpage as markdown

{
  "name": "web_fetch",
  "arguments": {
    "url": "https://example.com",
    "format": "markdown"
  }
}

Search the web

{
  "name": "web_search",
  "arguments": {
    "query": "latest JavaScript features 2026",
    "numResults": 5
  }
}

Development

# Type check
bunx tsc --noEmit

# Run in foreground
bun run src/index.ts

Architecture

• web_search proxies to Exa and Parallel MCP endpoints

• web_fetch uses native fetch with HTML→Markdown conversion (turndown) and Cloudflare fallback

• The MCP server uses @modelcontextprotocol/sdk with WebStandardStreamableHTTPServerTransport

• Listens on standard HTTP (no stdio required)

The web_search/web_fetch tool implementations were originally adapted from OpenCode's built-in web search tool, then extracted into this standalone server.

License

MIT