Skip to main content
Glama

Crawl4AI RAG MCP Server

by Chillbruhhh
MIT License
1
  • Apple
  • Linux
.env.example•2.88 kB
# The transport for the MCP server - either 'sse' or 'stdio' (defaults to sse if left empty) TRANSPORT= # Host to bind to if using sse as the transport (leave empty if using stdio) # Set this to 0.0.0.0 if using Docker, otherwise set to localhost (if using uv) HOST=0.0.0.0 # Port to listen on if using sse as the transport (leave empty if using stdio) PORT=8051 # Get your Open AI API Key by following these instructions - # https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key # This is for the embedding model - text-embed-small-3 will be used OPENAI_API_KEY= # Get your OpenRouter API Key from https://openrouter.ai/keys # This is for chat completions (summaries, contextual embeddings, code example summaries) OPENROUTER_API_KEY= # The LLM you want to use for summaries and contextual embeddings # Use OpenRouter model format like openai/gpt-4o-mini, anthropic/claude-3-haiku, etc. MODEL_CHOICE=openai/gpt-4o-mini # Optional: Your site URL and name for OpenRouter rankings (optional) YOUR_SITE_URL= YOUR_SITE_NAME=Crawl4AI-MCP # RAG strategies - set these to "true" or "false" (default to "false") # USE_CONTEXTUAL_EMBEDDINGS: Enhances embeddings with contextual information for better retrieval USE_CONTEXTUAL_EMBEDDINGS=true # USE_HYBRID_SEARCH: Combines vector similarity search with keyword search for better results USE_HYBRID_SEARCH=true # USE_AGENTIC_RAG: Enables code example extraction, storage, and specialized code search functionality USE_AGENTIC_RAG=true # USE_RERANKING: Applies cross-encoder reranking to improve search result relevance USE_RERANKING=true # USE_KNOWLEDGE_GRAPH: Enables AI hallucination detection and repository parsing tools using Neo4j # If you set this to true, you must also set the Neo4j environment variables below. USE_KNOWLEDGE_GRAPH=false # For the Supabase version (sample_supabase_agent.py), set your Supabase URL and Service Key. # Get your SUPABASE_URL from the API section of your Supabase project settings - # https://supabase.com/dashboard/project/<your project ID>/settings/api SUPABASE_URL= # Get your SUPABASE_SERVICE_KEY from the API section of your Supabase project settings - # https://supabase.com/dashboard/project/<your project ID>/settings/api # On this page it is called the service_role secret. SUPABASE_SERVICE_KEY= # Neo4j Configuration for Knowledge Graph Tools # These are required for the AI hallucination detection and repository parsing tools # Leave empty to disable knowledge graph functionality # Neo4j connection URI - use bolt://localhost:7687 for local, neo4j:// for cloud instances # IMPORTANT: If running the MCP server through Docker, change localhost to host.docker.internal NEO4J_URI=bolt://localhost:7687 # Neo4j username (usually 'neo4j' for default installations) NEO4J_USER=neo4j # Neo4j password for your database instance NEO4J_PASSWORD=password

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/Chillbruhhh/crawl4ai-mcp'

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