Crawl4AI+SearXNGSAFE
A self-contained MCP server in docker that combines the Crawl4AI, SearXNG, and Supabase to provide AI agents and coding assistants with complete web search, crawling, and RAG capabilities.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🐳 Crawl4AI+SearXNG MCP Server
Web Crawling, Search and RAG Capabilities for AI Agents and AI Coding Assistants
(FORKED FROM https://github.com/coleam00/mcp-crawl4ai-rag). Added SearXNG integration and batch scrape and processing capabilities.
A self-contained Docker solution that combines the Model Context Protocol (MCP), Crawl4AI, SearXNG, and Supabase to provide AI agents and coding assistants with complete web search, crawling, and RAG capabilities.
🚀 Complete Stack in One Command: Deploy everything with docker compose up -d - no Python setup, no dependencies, no external services required.
🎯 Smart RAG vs Traditional Scraping
Unlike traditional scraping (such as Firecrawl) that dumps raw content and overwhelms LLM context windows, this solution uses intelligent RAG (Retrieval Augmented Generation) to:
- 🔍 Extract only relevant content using semantic similarity search
- ⚡ Prevent context overflow by returning focused, pertinent information
- 🧠 Enhance AI responses with precisely targeted knowledge
- 📊 Maintain context efficiency for better LLM performance
Flexible Output Options:
- RAG Mode (default): Returns semantically relevant chunks with similarity scores
- Raw Markdown Mode: Full content extraction when complete context is needed
- Hybrid Search: Combines semantic and keyword search for comprehensive results
💡 Key Benefits
- 🔧 Zero Configuration: Pre-configured SearXNG instance included
- 🐳 Docker-Only: No Python environment setup required
- 🔍 Integrated Search: Built-in SearXNG for private, fast search
- ⚡ Production Ready: HTTPS, security, and monitoring included
- 🎯 AI-Optimized: RAG strategies built for coding assistants
Overview
This Docker-based MCP ser
9006c5b7070dOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add crawl4ai-mcp --env NEO4J_PASSWORD=${NEO4J_PASSWORD} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env SUPABASE_SERVICE_KEY=${SUPABASE_SERVICE_KEY} -- uvx crawl4ai-mcp{
"mcpServers": {
"crawl4ai-mcp": {
"command": "uvx",
"args": [
"crawl4ai-mcp"
],
"env": {
"NEO4J_PASSWORD": "${NEO4J_PASSWORD}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"SUPABASE_SERVICE_KEY": "${SUPABASE_SERVICE_KEY}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check_ai_script_hallucinations | read | |
get_available_sources | read | |
parse_github_repository | read | |
perform_rag_query | read | |
query_knowledge_graph | read | |
scrape_urls | read | |
search | read | |
search_code_examples | read | |
smart_crawl_url | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
9006c5b7070dfull audit observations/trust-audit/mcp-server/tokidoo__crawl4ai-searxng.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 9006c5b7070d | SAFE | B | 89 | first audit |
Questions
What is the Crawl4AI+SearXNG MCP server?
A self-contained MCP server in docker that combines the Crawl4AI, SearXNG, and Supabase to provide AI agents and coding assistants with complete web search, crawling, and RAG capabilities.
What tools does Crawl4AI+SearXNG expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Crawl4AI+SearXNG safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Crawl4AI+SearXNG need?
It reads NEO4J_PASSWORD, OPENAI_API_KEY and SUPABASE_SERVICE_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (9006c5b7070d), read on 2026-10-08. The repository is watched and re-audited when it changes.