MCP Server and CLI Tools for searxing and fetching websites
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"crawler": {
"cwd": "/path/to/searxNcrawl",
"env": {
"SEARXNG_URL": "http://your-searxng-instance:8888"
},
"args": [
"-m",
"crawler.mcp_server"
],
"command": "python"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
searxNcrawl is a minimal MCP server and CLI toolkit for search and crawling, built on top of Crawl4AI and SearXNG.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in search / browser
Web and local search using Brave Search API
Production ready MCP server with real-time search, extract, map & crawl.
Browser automation with Puppeteer for web scraping and testing
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
MCP Security Weekly
Get CVE alerts and security updates for SearxNcrawl and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
MCP server and CLI toolkit for web search and crawling, built on Crawl4AI and SearXNG.
Published at github.com/DasDigitaleMomentum/searxNcrawl — maintained by DDM – Das Digitale Momentum GmbH & Co KG. Successor to searxng-mcp.
Pick your setup:
SearXNG, Playwright, and the MCP server — one command.
cp .env.example .env # edit SEARXNG_URL if needed
docker compose up --build
➜ MCP server at http://localhost:9555/mcp
CLI tools, Python API, and MCP server. SearXNG required for search.
python -m venv .venv && source .venv/bin/activate
pip install -e .
playwright install chromium
Same capabilities as pip.
uv sync
uv run playwright install chromium
| Feature | Docker Compose | pip / uv |
|---|---|---|
| MCP Server (STDIO) | — | ✅ |
| MCP Server (HTTP) | ✅ | ✅ |
| Web Crawl | ✅ | ✅ |
| Web Search | ✅ (included) | ✅¹ |
| CLI Tools | via exec² | ✅ |
| Python API | — | ✅ |
| CORS (HTTP) | ✅ | ✅ |
¹ Requires a SearXNG instance. ² docker compose exec searxncrawl crawl ...
exact (default) removes repeated blocks, off disables it--remove-links)crawl — crawl pages from the command linesearch — search the web via SearXNGcrawl-capture — session capture for authenticated crawlingThe Compose stack includes searxNcrawl + SearXNG + Playwright/Chromium.
cp .env.example .env
# Edit .env: set SEARXNG_URL if using external SearXNG, or keep default
docker compose up --build
| Variable | Default | Description |
|---|---|---|
MCP_PORT | 9555 | MCP server HTTP port |
The MCP server is available at http://localhost:9555/mcp.
cd searxNcrawl
python -m venv .venv
source .venv/bin/activate
pip install -e .
playwright install chromium
cd searxNcrawl
uv sync
uv run playwright install chromium
The search tool and CLI command require a SearXNG instance with JSON output enabled (search.formats in settings.yml). Docker Compose includes one automatically. For pip/uv, you need your own — self-hosting is recommended over public instances (rate limits).
Environment variables:
| Variable | Default | Description |
|---|---|---|
SEARXNG_URL | http://localhost:8888 | SearXNG instance URL |
SEARXNG_USERNAME | (none) |