Crawl4AI RAG MCP Server
by utaschulz1
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 USE_KNOWLEDGE_GRAPH=true) | bolt://localhost:7687 |
| TRANSPORT | No | MCP transport type (sse or stdio) | sse |
| NEO4J_USER | No | Neo4j username (required if USE_KNOWLEDGE_GRAPH=true) | neo4j |
| MODEL_CHOICE | No | LLM model for summaries and contextual embeddings | gpt-4.1-nano |
| SUPABASE_URL | Yes | Your Supabase project URL | |
| USE_RERANKING | No | Enable cross-encoder reranking | false |
| NEO4J_PASSWORD | No | Neo4j password (required if USE_KNOWLEDGE_GRAPH=true) | |
| OPENAI_API_KEY | Yes | Your OpenAI API key for generating embeddings | |
| USE_AGENTIC_RAG | No | Enable agentic RAG for code examples | false |
| USE_HYBRID_SEARCH | No | Enable hybrid search (keyword + vector) | false |
| USE_KNOWLEDGE_GRAPH | No | Enable knowledge graph hallucination detection | false |
| SUPABASE_SERVICE_KEY | Yes | Your Supabase service role key | |
| USE_CONTEXTUAL_EMBEDDINGS | No | Enable contextual embeddings strategy | false |
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 | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/utaschulz1/mcp-crawl2db-neo4j-rag'
If you have feedback or need assistance with the MCP directory API, please join our Discord server