MCP Crawl4AI RAG
by rbj2000
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | MCP Server host | 0.0.0.0 |
| PORT | No | MCP Server port | 8051 |
| NEO4J_URI | No | Neo4j URI (required if knowledge graph enabled) | |
| TRANSPORT | No | MCP Server transport (sse or stdio) | sse |
| NEO4J_USER | No | Neo4j user (required if knowledge graph enabled) | |
| AI_PROVIDER | No | AI provider selection: openai, ollama, vllm, mixed | openai |
| LLM_PROVIDER | No | Override for LLM provider | |
| SUPABASE_URL | No | Supabase project URL (required if using Supabase) | |
| VLLM_API_KEY | No | vLLM API key | |
| USE_RERANKING | No | Enable reranking | false |
| VLLM_BASE_URL | No | vLLM base URL | |
| NEO4J_PASSWORD | No | Neo4j password (required if knowledge graph enabled) | |
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI) | |
| OLLAMA_BASE_URL | No | Ollama base URL | http://localhost:11434 |
| USE_AGENTIC_RAG | No | Enable agentic RAG | false |
| VLLM_TEXT_MODEL | No | vLLM text model | meta-llama/Llama-3.1-8B-Instruct |
| OLLAMA_LLM_MODEL | No | Ollama LLM model | llama3.2:1b |
| OPENAI_LLM_MODEL | No | OpenAI LLM model | gpt-4o-mini |
| USE_HYBRID_SEARCH | No | Enable hybrid search | false |
| EMBEDDING_PROVIDER | No | Override for embedding provider | |
| RERANKING_PROVIDER | No | Reranking provider: ollama, openai, huggingface | ollama |
| VECTOR_DB_PROVIDER | No | Vector database provider: supabase, sqlite, neo4j_vector, pinecone, weaviate | supabase |
| EMBEDDING_DIMENSION | No | Embedding dimension | 1536 |
| USE_KNOWLEDGE_GRAPH | No | Enable knowledge graph | false |
| VLLM_VISION_ENABLED | No | Enable vision models | false |
| SUPABASE_SERVICE_KEY | No | Supabase service key (required if using Supabase) | |
| VLLM_EMBEDDING_MODEL | No | vLLM embedding model | BAAI/bge-large-en-v1.5 |
| OLLAMA_EMBEDDING_MODEL | No | Ollama embedding model | nomic-embed-text |
| OPENAI_EMBEDDING_MODEL | No | OpenAI embedding model | text-embedding-3-small |
| USE_CONTEXTUAL_EMBEDDINGS | No | Enable contextual embeddings | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues