Skip to main content
Glama
clint419

websearch-mcp-server

by clint419

websearch-mcp-server

Standalone MCP server for Exa/Parallel free web search + URL content fetching. Works with Cursor, Claude Code, Cline, Continue, opencode, and any MCP-compatible AI client.

Tools

Tool

Description

websearch

Search the web via Exa or Parallel free MCP endpoints

webfetch

Fetch content from an HTTP/HTTPS URL as text/markdown/html

Related MCP server: perplexity-mcp

Install

npm install -g @clint419/websearch-mcp-server

From source

git clone https://github.com/clint419/websearch-mcp-server.git
cd websearch-mcp-server
npm install
npm run build

Configure

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "websearch": {
      "command": "npx",
      "args": ["-y", "@clint419/websearch-mcp-server"]
    }
  }
}

Claude Code

Add to ~/.claude/mcp.json:

{
  "mcpServers": {
    "websearch": {
      "command": "npx",
      "args": ["-y", "@clint419/websearch-mcp-server"]
    }
  }
}

Cline / Continue

Same pattern. Add to their MCP config with the command above.

Local development

{
  "command": "npx",
  "args": ["tsx", "/path/to/websearch-mcp-server/src/index.ts"]
}

HTTP Streamable (remote / shared)

Start the HTTP server:

npx @clint419/websearch-mcp-server-http
# or: npm run start:http

Add to MCP config:

{
  "mcpServers": {
    "websearch": {
      "url": "http://127.0.0.1:3000/mcp",
      "transport": "streamable-http"
    }
  }
}

Environment Variables

Variable

Values

Default

Description

WEBSEARCH_PROVIDER

exa, parallel

exa

Which upstream to use

EXA_API_KEY

string

(none)

Optional Exa API key

PARALLEL_API_KEY

string

(none)

Optional Parallel API key

MCP_PORT

number

3000

HTTP Streamable listen port

MCP_HOST

string

127.0.0.1

HTTP Streamable bind address

Source Structure

src/
  index.ts      – stdio MCP entry point
  http.ts       – HTTP Streamable MCP entry point (stateful)
  server.ts     – shared MCP server: tool registration
  websearch.ts  – Exa/Parallel MCP client with retry + failover
  webfetch.ts   – URL content fetcher (HTML→text/markdown conversion)

Reliability

  • Retry: Up to 2 retries with exponential backoff (1s, 2s) on network errors

  • Failover: If primary provider fails, automatically tries the other provider

  • Timeout: 25s per request

  • Free tier: No API key required by default

License

MIT

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    Enables web search using Perplexity AI's API, allowing users to search the web with optional recency filters and integration with Claude, Cursor, and other MCP clients.
    Last updated
    1
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables AI assistants to perform web searches and retrieve real-time information using Perplexity AI's Sonar models, with support for multiple search modes and easy integration with MCP clients.
    Last updated
    5
    1
    MIT

View all related MCP servers

Related MCP Connectors

  • Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding

  • Serper MCP — wraps the Serper Google Search API (serper.dev)

  • Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/clint419/websearch-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server