Skip to main content
Glama
Sign In
mcp-crawl4ai2vectordb

mcp-crawl4ai2vectordb

by utaschulz1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

mcp-crawl4ai2vectordb

MCP server for crawling web documentation and storing it in a Supabase vector database. Credits: craw4ai and Cole Medin's mcp server.

Responsibility: ingestion only — crawl, chunk, embed, store. No search, no reranking, no Neo4j.

Tools

Tool

Description

crawl_single_page

Crawl one URL and store its content

smart_crawl_url

Auto-detect URL type (sitemap / txt / webpage) and crawl accordingly

get_available_sources

List all sources stored in the database

delete_source

Delete a source and all its content from the database

Related MCP server: web-docs-mcp

Setup

cp .env.example .env
# fill in OPENAI_API_KEY, MODEL_CHOICE, SUPABASE_URL, SUPABASE_SERVICE_KEY
uv sync

Running

stdio (recommended — Claude Code manages the process):

Add to your MCP config:

{
  "mcpServers": {
    "crawl4ai2vectordb": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "python", "-u", "src/server.py"],
      "cwd": "/path/to/mcp_crawl4ai2vectordb"
    }
  }
}

or

{
  "mcpServers": {
    "crawl4ai2vectordb": {
      "type": "sse",
      "url": "http://localhost:8051/sse"
    }
  }
}

SSE (manual startup, for multi-client use):

TRANSPORT=sse uv run python -u src/server.py

Optional features

Env var

Default

Effect

USE_CONTEXTUAL_EMBEDDINGS

false

Prepend LLM-generated context to each chunk before embedding (improves retrieval accuracy, costs more)

USE_AGENTIC_RAG

false

Extract code blocks and store them separately in code_examples table

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessOutdated data

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches