Skip to main content
Glama
alexesom

Crawl4AI+SearXNG MCP Server

by alexesom

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHost address for MCP server0.0.0.0
PORTNoPort for MCP server8051
NEO4J_URINoNeo4j connection URI (required if USE_KNOWLEDGE_GRAPH=true)bolt://localhost:7687
TRANSPORTNoTransport protocol for MCP server (sse or stdio)sse
NEO4J_USERNoNeo4j username (required if USE_KNOWLEDGE_GRAPH=true)neo4j
SEARXNG_TLSNoEmail address for Let's Encrypt certificate (for production HTTPS)
SEARXNG_URLNoURL of the SearXNG server (pre-configured for Docker Compose)http://searxng:8080
MODEL_CHOICENoLLM model for summaries and contextual embeddingsgemini-2.5-flash-lite
SUPABASE_URLYesSupabase project URL for vector database (required)
USE_RERANKINGNoEnable reranking for improved result relevance using cross-encoder modelsfalse
GEMINI_API_KEYYesGemini API key for generating embeddings (required)
NEO4J_PASSWORDNoNeo4j password (required if USE_KNOWLEDGE_GRAPH=true)
SEARXNG_TIMEOUTNoTimeout for SearXNG requests in seconds30
USE_AGENTIC_RAGNoEnable specialized code example extraction and storagefalse
SEARXNG_HOSTNAMENoCustom domain for production HTTPS deploymenthttp://localhost
USE_HYBRID_SEARCHNoEnable hybrid search combining vector and keyword searchfalse
SEARXNG_USER_AGENTNoUser agent string for SearXNG requestsMCP-Crawl4AI-RAG-Server/1.0
USE_KNOWLEDGE_GRAPHNoEnable AI hallucination detection and repository code analysis using Neo4jfalse
SUPABASE_SERVICE_KEYYesSupabase service key for vector database (required)
SEARXNG_DEFAULT_ENGINESNoDefault search engines for SearXNGgoogle,bing,duckduckgo
USE_CONTEXTUAL_EMBEDDINGSNoEnable contextual embeddings for enhanced semantic understandingfalse

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/alexesom/crawl4ai-rag-mcp-gemini'

If you have feedback or need assistance with the MCP directory API, please join our Discord server