io.github.yokingma/one-search-mcp

Official

by yokingma · TypeScript

Web search, crawl, scrape & extract with agent-browser, SearXNG, Tavily, DuckDuckGo, Bing & more

Web search, crawl, scrape, and extract data from multiple search engines.

Topics

mcp-servermodelcontextprotocolbing-mcpduckduckgo-mcpsearxng-mcptavily-mcpagent-browsergoogle-search-mcp

README.md10 KBView on GitHub

🚀 OneSearch MCP Server: Web Search, URL Discovery, Scraper & Content Prep

A Model Context Protocol (MCP) server implementation that integrates with multiple search providers for web search, local browser search, URL discovery, and scraping capabilities with agent-browser.

Features

Web search, scrape, discover URLs, and preprocess content from websites.
Support multiple search engines and web scrapers: SearXNG, Tavily, DuckDuckGo, Bing, Google, Zhipu (智谱), Exa, Bocha (博查), etc.
Local web search (browser search), support multiple search engines: Bing, Google, Baidu, Sogou, etc.
- Use agent-browser for browser automation.
- Free, no API keys required.
Enabled tools: one_search, one_scrape, one_map, one_extract

Current Tool Surface

one_search
- Returns search results from the configured provider.
one_map
- Discovers links from a starting URL by loading the page in the browser and extracting links from its HTML.
- Supported input fields: url, search, includeSubdomains, limit.
- This is not a sitemap crawler; removed fields such as ignoreSitemap and sitemapOnly are rejected at the schema boundary.
one_scrape
- Scrapes one page and returns content selected by formats.
- Supported input fields: url, formats, waitFor, timeout, skipTlsVerification, allowExecuteJavascript, actions.
- Supported formats: markdown, html, rawHtml, links, screenshot, screenshot@fullPage.
- Supported bounded pre-scrape actions: wait, click, write, press, scroll.
- Advanced pre-scrape action: executeJavascript. If actions contains executeJavascript, you must set allowExecuteJavascript: true.
- actions run serially before content capture and fail fast on the first action error.
- Removed fields such as onlyMainContent, extract, and location are rejected at the schema boundary.
one_extract
- Accepts only urls and returns preprocessed text blocks for downstream tools or models.

Migration from v1.1.0 and Earlier

Breaking Changes in v1.1.0:

Firecrawl Removed: The Firecrawl integration has been removed in favor of agent-browser, which provides similar functionality without requiring external API services.
New Browser Requirement: You must install Chromium browser (see Prerequisites section).
Environment Variables: FIRECRAWL_API_URL and FIRECRAWL_API_KEY are no longer used.

What Changed:

one_scrape and one_map now use agent-browser instead of Firecrawl
one_extract now preprocesses multi-URL page content for downstream analysis instead of performing built-in LLM extraction
All browser-based operations are now handled locally, providing better privacy and no API costs

Migration Steps:

Install Chromium browser (see Prerequisites)
Remove FIRECRAWL_API_URL and FIRECRAWL_API_KEY from your environment variables
Update to the latest version: npm install -g one-search-mcp@latest

Prerequisites

Browser Requirement: This server uses agent-browser for web scraping and local search, which requires a Chromium-based browser.

Good News: The server will automatically detect and use browsers already installed on your system:

✅ Google Chrome
✅ Microsoft Edge
✅ Chromium
✅ Google Chrome Canary

If you don't have any of these browsers installed, you can:

bash

# Option 1: Install Google Chrome (Recommended)
# Download from: https://www.google.com/chrome/

# Option 2: Install Microsoft Edge
# Download from: https://www.microsoft.com/edge

# Option 3: Install Chromium via agent-browser
npx agent-browser install

# Option 4: Install Chromium directly
# Download from: https://www.chromium.org/getting-involved/download-chromium/

Installation

Using Claude Code CLI (Recommended)

bash

# Add to Claude Code with default settings (local search)
claude mcp add one-search-mcp -- npx -y one-search-mcp

# Add with custom search provider (e.g., SearXNG)
claude mcp add one-search-mcp -e SEARCH_PROVIDER=searxng -e SEARCH_API_URL=http://127.0.0.1:8080 -- npx -y one-search-mcp

# Add with Tavily API
claude mcp add one-search-mcp -e SEARCH_PROVIDER=tavily -e SEARCH_API_KEY=your_api_key -- npx -y one-search-mcp

Manual Installation

bash

# Install globally (Optional)
npm install -g one-search-mcp

# Or run directly with npx
npx -y one-search-mcp

Local Debugging with MCP Inspector

Use the official MCP Inspector to interactively test tools, resources, and prompts against this server during local development.

bash

# Inspect the TypeScript source entrypoint
npm run inspector

# Inspect the built server entrypoint
npm run inspector:build

# Example with explicit environment variables
ALLOW_PRIVATE_NETWORK=true SEARCH_PROVIDER=local npm run inspector

Using Docker

Docker image includes all dependencies (Chromium browser) pre-installed, no additional setup required.

Pull the image:

bash

# From GitHub Container Registry
docker pull ghcr.io/yokingma/one-search-mcp:latest

# Or from Docker Hub
docker pull zacma/one-search-mcp:latest

Configure with Claude Desktop:

json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/yokingma/one-search-mcp:latest"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

With custom search provider:

json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "SEARCH_PROVIDER=tavily",
        "-e", "SEARCH_API_KEY=your_api_key",
        "ghcr.io/yokingma/one-search-mcp:latest"
      ]
    }
  }
}

Environment Variables

Search Provider

SEARCH_PROVIDER (Optional): The search provider to use, supports searxng, duckduckgo, bing, tavily, google, zhipu, exa, bocha, local, default is local.
SEARCH_API_URL (Optional): The URL of the SearxNG API, or Google Custom Search Engine ID for google.
SEARCH_API_KEY (Optional): The API key for the search provider, required for tavily, bing, google, zhipu, exa, bocha.

// supported search providers
export type SearchProvider = 'searxng' | 'duckduckgo' | 'bing' | 'tavily' | 'google' | 'zhipu' | 'exa' | 'bocha' | 'local';

Browser Network Security

ALLOW_PRIVATE_NETWORK (Optional): Set to true to allow browser-backed tools (one_scrape, one_map, one_extract) to access private, loopback, and link-local network targets. Defaults to false.

Use ALLOW_PRIVATE_NETWORK=true only in trusted deployments. When enabled, prompt injection or untrusted tool inputs can make the MCP process fetch internal services that are otherwise blocked by default.

Search Provider Configuration

Provider	API Key Required	API URL Required	Notes
`local`	No	No	Free, uses browser automation
`duckduckgo`	No	No	Free, no API key needed
`searxng`	Optional	Yes	Self-hosted meta search engine
`bing`	Yes	No	Bing Search API
`tavily`	Yes	No	Tavily API
`google`	Yes	Yes (Search Engine ID)	Google Custom Search
`zhipu`	Yes	No	智谱 AI
`exa`	Yes	No	Exa AI
`bocha`	Yes	No	博查 AI

Configuration for Other MCP Clients

Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": ["-y", "one-search-mcp"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

Cursor

Add to your mcp.json file:

json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": ["-y", "one-search-mcp"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

Windsurf

Add to your ./codeium/windsurf/model_config.json file:

json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": ["-y", "one-search-mcp"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

Self-hosting SearXNG (Optional)

If you want to use SearXNG as your search provider, you can deploy it locally using Docker:

Prerequisites:

Docker installed and running (version 20.10.0 or higher)
At least 4GB of RAM available

Quick Start:

bash

# Clone SearXNG Docker repository
git clone https://github.com/searxng/searxng-docker.git
cd searxng-docker

# Start SearXNG
docker compose up -d

After deployment, SearXNG will be available at http://127.0.0.1:8080 by default.

Configure OneSearch to use SearXNG:

bash

# Set environment variables
export SEARCH_PROVIDER=searxng
export SEARCH_API_URL=http://127.0.0.1:8080

For more details, see the official SearXNG Docker documentation.

Troubleshooting

Browser not found error

If you see an error like "Browser not found", the server couldn't detect any installed Chromium-based browser. Please install one of the following:

Google Chrome: https://www.google.com/chrome/
Microsoft Edge: https://www.microsoft.com/edge
Chromium: https://www.chromium.org/getting-involved/download-chromium/

Or install via agent-browser:

bash

npx agent-browser install

License

MIT License - see LICENSE file for details.

Install

Configuration

Environment variables

SEARCH_PROVIDER

Search provider to use (searxng, duckduckgo, bing, tavily, google, zhipu, exa, bocha, local)

SEARCH_API_URL

API URL for SearXNG (required if using searxng provider), or Google Custom Search Engine ID for google

SEARCH_API_KEYsecret

API key for search provider (required for tavily, bing, google, zhipu, exa, bocha)

ALLOW_PRIVATE_NETWORK

Allow browser-backed tools to access private, loopback, and link-local network targets when set to true

claude_desktop_config.json

{
  "mcpServers": {
    "one-search-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "one-search-mcp@1.2.2"
      ],
      "env": {
        "SEARCH_PROVIDER": "<YOUR_SEARCH_PROVIDER>",
        "SEARCH_API_URL": "<YOUR_SEARCH_API_URL>",
        "SEARCH_API_KEY": "<YOUR_SEARCH_API_KEY>",
        "ALLOW_PRIVATE_NETWORK": "<YOUR_ALLOW_PRIVATE_NETWORK>"
      }
    }
  }
}