Web Research MCP Server
Provides web search capabilities via DuckDuckGo without requiring an API key, enabling AI agents to search the web and retrieve search results programmatically.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Web Research MCP Serverresearch the latest AI safety guidelines from leading labs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
By MEOK AI Labs — Sovereign AI tools for everyone.
Web Research MCP Server
Web search and browser automation toolkit for AI agents. Search the web via DuckDuckGo (no API key), browse pages with headless Chromium, extract article content, take screenshots, interact with forms, and run multi-step research workflows that search and read multiple pages automatically.
Tools
Tool | Description |
| DuckDuckGo search -- no API key required |
| Full browser automation: extract, screenshot, click, type, PDF |
| Clean article extraction (strips nav/ads/boilerplate) |
| Multi-step workflow: search + read top N pages + compile brief |
| Current weather for any location (wttr.in) |
Installation
pip install mcp httpx playwright duckduckgo-search
python -m playwright install chromiumThe duckduckgo-search package is optional -- the server falls back to HTML scraping if not installed. Playwright + Chromium is required for browse_page, extract_article, and research_topic.
Usage
Run the server
python server.pyClaude Desktop config
{
"mcpServers": {
"web-research": {
"command": "python",
"args": ["/path/to/web-research-mcp/server.py"]
}
}
}Example calls
Web search:
Tool: web_search
Input: {"query": "best practices for MCP server development", "limit": 5}
Output: {"results": [{"title": "...", "url": "...", "snippet": "..."}], "query": "...", "engine": "duckduckgo"}Browse and extract page:
Tool: browse_page
Input: {"url": "https://example.com/article", "action": "extract"}
Output: {"status": "ok", "title": "...", "text": "...", "links": [...]}Take screenshot:
Tool: browse_page
Input: {"url": "https://example.com", "action": "screenshot"}
Output: {"status": "ok", "image_base64": "...", "full_size_bytes": 142531}Research a topic (automated):
Tool: research_topic
Input: {"query": "MCP protocol specification 2026", "depth": 3}
Output: {"pages_searched": 5, "pages_read": 3, "sources": [...], "brief": "# Research: ..."}Pricing
Tier | Limit | Price |
Free | 25 calls/day | $0 |
Pro | Unlimited + full screenshots + PDF export | $9/mo |
Enterprise | Custom + proxy rotation + CAPTCHA solving | Contact us |
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
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/CSOAI-ORG/web-research-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server