Allows searching for academic preprints and papers via the arXiv API.
Allows using Brave Search API for independent web search results, enhancing search quality (optional, requires API key).
Allows searching community content from CSDN, a Chinese developer community, used in parallel search expansion.
Allows searching for GitHub repositories and issues as part of code search, leveraging Bing as backend.
Allows searching for computer science papers and citations via Semantic Scholar, with fallback to arXiv.
Allows searching Wikipedia for definitions, facts, and encyclopedic content.
Allows searching community content from Zhihu, a Chinese Q&A platform, used in parallel search expansion.
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 Tools MCP search for quantum computing breakthroughs"
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.
Multi-engine web search and content extraction MCP server for AI agents. Drop-in replacement for native web_search / web_fetch tools, compatible with any LLM connected to Grok Build, Claude Code, Cursor, or other MCP hosts.
10 classified data sources — Bing, 360 Search, Wikipedia, arXiv, Semantic Scholar, StackOverflow, Hacker News, Brave (optional), comprehensive hybrid, code search
4-way parallel multi-angle search — each query auto-expands into 4 complementary search angles, executed concurrently via asyncio.gather
Content-first extraction — Jina Reader returns clean Markdown from any URL; BeautifulSoup fallback for html pages
Smart TTL caching — search results cached for 5 min, fetched pages for 30 min; ~3000x speedup on cache hits
Zero API keys required — all sources work out of the box; optional Brave Search API key for independent search index
Drop-in compatible — same tool names and parameter schema as native Grok web_search/web_fetch
Related MCP server: mcp-jina-reader
Python 3.11+
Grok Build / Claude Code / Cursor / any MCP-compatible host
git clone https://github.com/hellowind777/web-tools-mcp.git
cd web-tools-mcp
pip install -r requirements.txtAdd to ~/.grok/config.toml (or equivalent MCP host config):
[mcp_servers.web-tools]
command = "python"
args = ["/path/to/web-tools-mcp/mcp_server/server.py"]
enabled = true
startup_timeout_sec = 30
tool_timeout_sec = 30Restart your MCP host. The tools web-tools__web_search and web-tools__web_fetch become available to your model.
For higher-quality results from an independent search index:
export BRAVE_API_KEY="your-key-here"Get a free key at brave.com/search/api (2000 queries/month free).
Classified search with 10 source options. Automatically runs 4-angle parallel queries for web/comprehensive/news sources.
Parameter | Type | Default | Description |
| string | required | Search query |
| string |
| Data source (see below) |
| integer | 10 | Results to return |
Available sources:
Source | Backend | Best for |
| Bing (or Brave if key set) | General search |
| Bing + Wikipedia + arXiv | Research topics |
| Wikipedia API | Definitions, facts |
| Semantic Scholar → arXiv fallback | CS papers, citations |
| arXiv API | Preprints, papers |
| GitHub via Bing | Repos, issues |
| StackExchange API | Q&A with scores |
| HN Algolia API | Tech news, discussions |
| 360 Search (so.com) | Chinese-language content |
| Bing (semantic alias) | News queries |
Fetch and extract readable content from any URL.
Parameter | Type | Default | Description |
| string | required | URL to fetch |
| integer | 8000 | Max characters returned |
Uses Jina Reader as primary backend (clean Markdown, handles JS pages), falls back to BeautifulSoup HTML extraction.
web_search(query, source) web_fetch(url)
│ │
┌────▼────┐ ┌──────────▼──────────┐
│ Cache │ │ Jina Reader (1st) │
│ TTL 300s │ │ BeautifulSoup (2nd) │
└────┬────┘ └──────────┬──────────┘
│ │
┌────▼──────────────────────────────▼──┐
│ Data Source Layer │
│ │
│ Bing ─── 360 ─── Wikipedia ─── arXiv │
│ Scholar ─── StackOverflow ─── HN │
│ Brave (optional) ─── Comprehensive │
└───────────────────────────────────────┘For web/comprehensive/news sources, each query is expanded into 4 parallel searches:
Original query
Official documentation
Community sources (GitHub/CSDN/Zhihu)
Latest (year-aware freshness)
Web Tools MCP | Tavily MCP | Brave MCP | Exa MCP | |
Free tier | ✅ Unlimited | 1000/mo | 2000/mo | Trial only |
Sources | 10 | 1 | 1 | 1 |
Parallel multi-angle | ✅ 4-way |
| Single query | Single query |
Content extraction | ✅ Jina+BS4 |
| None | None |
API key required | ❌ | ✅ | ✅ | ✅ |
Chinese support | ✅ 360 search | ❌ | ❌ | ❌ |
Academic | ✅ arXiv+Scholar | ❌ | ❌ | ❌ |
# Install dev dependencies
pip install -r requirements.txt
# Run tests (manual — MCP protocol)
python mcp_server/server.pyApache-2.0
This server cannot be deployed
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
MCP server for Google search results via SERP API
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
