Advertise
MCP.so
Sign In

MCP Web Search Tool

@gabrimatic

RepositoryHomepage

Basic information

Category

Search

License

MIT

Transports

stdio

Author

gabrimatic

About MCP Web Search Tool

A MCP server providing real-time web search capabilities to any AI model.

#agent#mcp#claude#search-agent#claude-ai#websearch-agent#model-context-protocol#mcp-server

MCP Web Search Tool config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-web-search-tool": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp-web-search",
        "."
      ]
    }
  }
}

MCP Web Search Tool tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Web Search Tool?

MCP Web Search Tool is an MCP server that lets AI assistants perform live web searches, read full page content, and retrieve source citations. It uses stdio transport, has pluggable providers, and requires no scraper dependencies.

How to use MCP Web Search Tool?

Clone the repository, install dependencies with npm, copy the .env.example file and optionally set BRAVE_API_KEY, then build and start. Docker is also supported. For client integration (Claude Desktop, VS Code, Cursor, etc.), see MCP_CLIENTS.md.

Key features of MCP Web Search Tool

  • Five tools: web_search, news_search, image_search, fetch_url, list_providers
  • Search returns ranked summaries with stable IDs and structured JSON
  • Primary provider is Brave Search; keyless DuckDuckGo fallback for web search
  • fetch_url strips scripts, styles, nav, footer, and aside from page text
  • Configurable caching (LRU+TTL) for both search and URL fetch results
  • Environment‑driven configuration for timeouts, limits, and provider selection

Use cases of MCP Web Search Tool

  • Get current, source‑backed answers to live questions during a conversation
  • Research topics by searching and reading full articles with cited sources
  • Find recent news with source name and publish date via news_search
  • Retrieve images with thumbnails for visual queries
  • Integrate real‑time web data into AI assistant workflows without additional scraping tools

Frequently asked questions

1

What are the runtime requirements?

Node.js >= 20.18 and npm >= 10. The server uses native `fetch` and has no other scraper dependencies.

2

Do I need a Brave Search API key?

No. Without a key, `web_search` runs on DuckDuckGo as a keyless fallback. However, `news_search` and `image_search` require a Brave key. Set `ALLOW_KEYLESS=false` to refuse startup without a key.

3

What does `fetch_url` refuse to fetch?

It rejects non‑`http(s)` schemes and any host that resolves to private, loopback, link‑local, multicast, or IPv4‑mapped IPv6 private addresses (see `SECURITY.md`).

4

Which search providers are available?

Brave Search (default when `BRAVE_API_KEY` is set) and DuckDuckGo (keyless fallback). Call `list_providers` to check availability of news and image search in the current session.

5

How can I configure caching?

Via environment variables: `CACHE_MAX_ENTRIES` (default 256) and `CACHE_TTL_MS` (default 300 000) for search cache; `FETCH_CACHE_MAX` (default 128) and `FETCH_CACHE_TTL_MS` (default 600 000) for URL fetch cache.

Comments

More Search MCP servers

CUQU找搭子 MCP（粗趣）

cuqu-net

CUQU找搭子官方 Agent Skill：让任意 AI Agent（Claude Code/Codex/Cursor/WorkBuddy）代用户找同城线下局、报名、支付、发局。MCP Streamable HTTP + 个人 API Key 网关 agent.cuqu.net

Singapore Proxy

Singapore Mobile Proxy

Give Claude, Cursor or any MCP agent a real Singapore mobile IP. Fetch pages, run Singapore-localised Google searches and check geo-locked content through physical Singtel and M1 SIMs, with IP rotation on demand. Hosted

patent-literature-search-mcp

patsnap

A professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.

1

Google Search MCP Server

HasData

Hosted Google Search / SERP MCP server from HasData, no Google Cloud project. Organic results, AI Overview, People Also Ask, AI Mode, news and shopping for Claude, Cursor and any MCP client.

23

Opsis OSINT

Opsis LLC

OSINT search for AI agents. Find the accounts behind an email, username or domain across 1,000+ sources, with verified profiles: names, photos, bios, locations, stats and linked accounts. An account only counts when the

Advertise