Skip to main content
Glama

Crawl4AI+SearXNG MCP Server

by ToKiDoO

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHost address for the MCP server0.0.0.0
PORTNoPort for the MCP server8051
NEO4J_URINoNeo4j database URI for knowledge graphbolt://localhost:7687
TRANSPORTNoTransport protocol for the MCP serversse
NEO4J_USERNoNeo4j username for knowledge graphneo4j
SEARXNG_TLSNoEmail for Let's Encrypt SSL certificate
SEARXNG_URLNoURL of the SearXNG search enginehttp://searxng:8080
MODEL_CHOICENoLLM model for summaries and contextual embeddingsgpt-4.1-nano-2025-04-14
SUPABASE_URLYesSupabase project URL for vector database
USE_RERANKINGNoEnable reranking for improved result relevancefalse
NEO4J_PASSWORDNoNeo4j password for knowledge graph
OPENAI_API_KEYYesOpenAI API key for embeddings
SEARXNG_TIMEOUTNoTimeout for SearXNG requests30
USE_AGENTIC_RAGNoEnable agentic RAG for code example extractionfalse
SEARXNG_HOSTNAMENoHostname for SearXNG in productionhttp://localhost
USE_HYBRID_SEARCHNoEnable hybrid search combining vector and keyword searchfalse
SEARXNG_USER_AGENTNoUser agent for SearXNG requestsMCP-Crawl4AI-RAG-Server/1.0
USE_KNOWLEDGE_GRAPHNoEnable knowledge graph for hallucination detectionfalse
SUPABASE_SERVICE_KEYYesSupabase service key for vector database
SEARXNG_DEFAULT_ENGINESNoDefault search engines for SearXNGgoogle,bing,duckduckgo
USE_CONTEXTUAL_EMBEDDINGSNoEnable contextual embeddings for RAG enhancementfalse

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/ToKiDoO/crawl4ai-rag-mcp'

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