Web Research MCP Server
This server provides web research and browser automation capabilities for searching, reading, extracting, and synthesizing web content.
Search the web via DuckDuckGo and return top result titles, URLs, and snippets without an API key.
Browse webpages with headless Chromium/Playwright: extract page text/links, take screenshots, click elements, type text, and save pages as PDFs.
Extract clean article text from URLs, stripping navigation, ads, and boilerplate.
Run multi-step research by searching and extracting content from top results into a compiled brief with sources.
Perform deeper autonomous research loops that search, read pages, and synthesize findings.
Get current weather for a location via wttr.in.
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 "Deploy 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 Server research 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.
Web Research MCP
mcp-name: io.github.CSOAI-ORG/web-research-mcp
Web Research MCP Server
By MEOK AI Labs ā Sovereign AI tools for everyone.
Web search and browser automation toolkit: DuckDuckGo search, page extraction, screenshots, click...
Web search and browser automation toolkit: DuckDuckGo search, page extraction, screenshots, click/type automation, and article reader.
š Quick Start
# Install via pip
pip install web_research_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install web-research-mcp --client claudeRelated MCP server: Search Proxy MCP
⨠Features
MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance
š Documentation
š”ļø Compliance
This MCP server is built with EU AI Act compliance built-in:
ā Article 9 ā Risk Management System
ā Article 13 ā Transparency & Instructions for Use
ā Article 15 ā Bias Detection & Testing
ā Article 26 ā FRIA Support (where applicable)
ā Article 50 ā AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic ā
How MEOK charges
MEOK has no subscriptions and no tiers. You pay per job, and only when the agreed artifact has been delivered to you. There is no public price list. See https://meok.ai/pricing.
This repository's source is MIT-licensed and free to self-host.
š¤ Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem ā 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
š License
MIT Ā© CSOAI-ORG
Quick Install
Client | Install |
Claude Desktop | |
Cursor | |
VS Code | |
Windsurf | |
Docker |
|
pip |
|
Tools
Tool | Description |
| Search the web using DuckDuckGo (no API key needed) |
| Browse a webpage using headless Chromium (Playwright) |
| Extract clean, readable article text from a URL |
| Multi-step research: search the web, then extract content |
| Get current weather for a location via wttr.in |
Quick Start
pip install mcp
git clone https://github.com/CSOAI-ORG/web-research-mcp.git
cd web-research-mcp
python server.pyClaude Desktop Config
{
"mcpServers": {
"web-research": {
"command": "python",
"args": ["server.py"],
"cwd": "/path/to/web-research-mcp"
}
}
}Part of MEOK AI Labs
This is one of 255+ MCP servers by MEOK AI Labs. Browse all at meok.ai or GitHub.
MEOK AI Labs | meok.ai | nicholas@meok.ai | United Kingdom
Pairs with MEOK Governance Suite
Build something that touches users? You need compliance. MEOK ships 38 governance MCPs that drop in alongside this tool ā EU AI Act, DORA, NIS2, CRA, GDPR, ISO 42001, FDA SaMD, MDR, Basel, MiFID II, MiCA, COPPA, and more.
# One-shot install of the governance pack
npx meok-setup --pack governanceā Full catalogue: councilof.ai ā MEOK AI Labs: meok.ai
Available Tools
7 toolsautonomous_researchC
Run an autonomous multi-step research loop on a topic.
Inputs: topic (required), depth, api_key. Returns: result
browse_pageC
Browse a webpage using a headless Chromium browser (Playwright). Actions:
extract: Get page title, description, text content, and links
screenshot: Capture a screenshot (base64 PNG)
click: Click on element matching instruction text
type: Type text into input (format: 'text to type into selector')
pdf: Save page as PDF (base64) Requires: playwright installed with chromium.
Inputs: url (required), action, instruction, api_key.
deep_researchB
Autonomous multi-step research. Searches, reads pages, synthesizes findings.
Inputs: topic (required), depth, api_key. Returns: result
extract_articleB
Extract clean, readable article text from a URL. Strips navigation, ads, and boilerplate. Returns title, article text, word count, and paragraph count.
Inputs: url (required), api_key.
get_weatherA
Get current weather for a location using wttr.in (no API key needed).
Inputs: location, api_key.
research_topicB
Multi-step research workflow: search the web, then extract content from the top results. Returns a compiled research brief with sources. Depth controls how many pages to read (1-5).
Inputs: query (required), depth, api_key.
web_searchA
Search the web using DuckDuckGo. Returns titles, URLs, and snippets for the top results. No API key required.
Inputs: query (required), limit, api_key.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 7 tools
The tools autonomous_research, deep_research, and research_topic are essentially the same multi-step research workflow, causing confusion. Additionally, get_weather is unrelated to web research, further muddying the tool set's purpose.
While all tool names use snake_case, the verb-noun pattern is inconsistent: some are verb_noun (browse_page, extract_article), others are adjective_noun (autonomous_research, deep_research), noun_verb (web_search), or noun_noun (research_topic). The mix is noticeable but not chaotic.
With 7 tools, the count is appropriate for a focused web research server. It covers the main operations without being overwhelming, though redundant research tools could be consolidated.
The server covers key research steps: search, browse, extract, and synthesize. However, the three overlapping research tools suggest poor design and missed opportunities for distinct operations like saving results or managing sessions. The weather tool is off-topic.
Maintenance
Related MCP Connectors
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Web scraping, search, crawling, structured extraction and research for AI agents.
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables web searching through Google, DuckDuckGo, and Bing using a headless Chrome browser, returning structured results with titles, URLs, and snippets. Also supports fetching and extracting text content from any webpage.16MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI agents to search the web, find news, and read page content via DuckDuckGo without an API key.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to perform query-driven web searches and fetch page content via Bing and DuckDuckGo engines, with automatic fallback and no API keys needed.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search the internet using DuckDuckGo and extract clean, formatted content from web pages.GPL 3.0