/ 100

9 days ago

glama

MCP Crawl4AI RAG

A database-agnostic MCP server that integrates web crawling with Retrieval Augmented Generation, supporting multiple AI providers and vector database backends for flexible and intelligent content retrieval.

→ rbj2000/mcp-crawl4ai-rag · listed on glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 14 credentials: NEO4J_PASSWORD, HUGGINGFACE_TOKEN, OPENAI_API_KEY, ANTHROPIC_API_KEY, COHERE_API_KEY, HUGGINGFACE_API_KEY, VLLM_API_KEY, CONFLUENCE_API_TOKEN, CONFLUENCE_OAUTH2_CLIENT_SECRET, CONFLUENCE_OAUTH2_ACCESS_TOKEN, CONFLUENCE_OAUTH2_REFRESH_TOKEN, SUPABASE_SERVICE_KEY, PINECONE_API_KEY, WEAVIATE_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configENABLE_MONITORING

configCOMPOSE_PROFILES

configNEO4J_URI— bolt://localhost:7687

configNEO4J_USER— "": "neo4j",

🔐 secretNEO4J_PASSWORD— your_neo4j_password

configUSE_RERANKING

configRERANKING_PROVIDER— ollama # Options: ollama, openai, huggingface

configRERANKING_MODEL

configRERANKING_MAX_RESULTS

configRERANKING_TIMEOUT

🔐 secretHUGGINGFACE_TOKEN

configAI_PROVIDER— export =openai # or ollama, vllm

🔐 secretOPENAI_API_KEY— export =your_key # For OpenAI provider

configOPENAI_BASE_URL

configOPENAI_ORGANIZATION

configOPENAI_MAX_RETRIES

configOPENAI_TIMEOUT

configOLLAMA_BASE_URL

configOLLAMA_MAX_RETRIES

configOLLAMA_TIMEOUT

configOLLAMA_PULL_MODELS

🔐 secretANTHROPIC_API_KEY

configANTHROPIC_BASE_URL

configANTHROPIC_MAX_RETRIES

configANTHROPIC_TIMEOUT

🔐 secretCOHERE_API_KEY

configCOHERE_BASE_URL

configCOHERE_MAX_RETRIES

configCOHERE_TIMEOUT

🔐 secretHUGGINGFACE_API_KEY

configHUGGINGFACE_MAX_RETRIES

configHUGGINGFACE_TIMEOUT

configVLLM_BASE_URL

🔐 secretVLLM_API_KEY— your_vllm_api_key

configVLLM_MAX_RETRIES

configVLLM_TIMEOUT

configVLLM_VISION_ENABLED— false # Enable vision models (coming soon)

configCONFLUENCE_URL

configCONFLUENCE_SSL_VERIFY

configCONFLUENCE_CA_BUNDLE

configCONFLUENCE_TIMEOUT

configCONFLUENCE_CONNECT_TIMEOUT

configCONFLUENCE_POOL_SIZE

configCONFLUENCE_MAX_RETRIES

configCONFLUENCE_DEPLOYMENT_TYPE

configCONFLUENCE_AUTH_METHOD

configCONFLUENCE_OAUTH2_CLIENT_ID

configCONFLUENCE_PAT

🔐 secretCONFLUENCE_API_TOKEN

configCONFLUENCE_USERNAME

🔐 secretCONFLUENCE_OAUTH2_CLIENT_SECRET

🔐 secretCONFLUENCE_OAUTH2_ACCESS_TOKEN

🔐 secretCONFLUENCE_OAUTH2_REFRESH_TOKEN

configCONFLUENCE_OAUTH2_TOKEN_EXPIRES_AT

configCONFLUENCE_CLOUD_ID

configCONFLUENCE_MAX_PAGES

configCONFLUENCE_MAX_DEPTH

configUSE_AGENTIC_RAG

configCONFLUENCE_SKIP_UNCHANGED

configUSE_KNOWLEDGE_GRAPH— ## Knowledge Graph Tools (requires =true, see below)

configHOST

configPORT— docker build -t mcp/crawl4ai-rag --build-arg =8051 .

configOLLAMA_EMBEDDING_MODEL— nomic-embed-text

configOLLAMA_LLM_MODEL— llama3.2:1b

configVECTOR_DB_PROVIDER— export =sqlite # or supabase, pinecone, neo4j_vector

configSQLITE_DB_PATH

configSUPABASE_URL— your_supabase_project_url

🔐 secretSUPABASE_SERVICE_KEY— your_supabase_service_key

configUSE_HYBRID_SEARCH

configTRANSPORT— "": "stdio",

configEMBEDDING_DIMENSION— 1536 # Must match your embedding model dimensions

configOPENAI_EMBEDDING_MODEL— text-embedding-3-small

🔐 secretPINECONE_API_KEY

configPINECONE_ENVIRONMENT

configPINECONE_INDEX_NAME

configWEAVIATE_URL

🔐 secretWEAVIATE_API_KEY

configWEAVIATE_CLASS_NAME

configNEO4J_DATABASE

configMODEL_CHOICE

configUSE_CONTEXTUAL_EMBEDDINGS

configGENERATE_TEST_REPORT

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/rbj2000-mcp-crawl4ai-rag-1aoa6o)](https://m8ven.ai/mcp/rbj2000-mcp-crawl4ai-rag-1aoa6o)

commit: f37bb8b2572198e69048cff1b741b518d3ac661a

code hash: b2dc4a151081addb40ee7ed6be5ed443291cfb83bc02cfd52b7cf6983f691f41

verified: 6/21/2026, 10:32:37 AM

view raw JSON →