Set up Weaviate MCP in VS Code
Connect to Weaviate vector database collections for semantic search, knowledge base operations, and chat memory storage from your AI editor.
1
Locate the config file
VS Code reads MCP server configuration from the following file:
.vscode/settings.json → mcp sectionCreate this file if it does not already exist. For VS Code, this is inside your workspace .vscode/settings.json file under the mcp section.
2
Add the configuration
Add the following to your VS Code config file:
json
{
"servers": {
"weaviate-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-server-weaviate"
],
"env": {
"WEAVIATE_URL": "YOUR_WEAVIATE_URL",
"WEAVIATE_API_KEY": "YOUR_WEAVIATE_API_KEY"
}
}
}
}3
Set up environment variables
Weaviate MCP requires the following environment variables:
WEAVIATE_URLRequiredWeaviate instance URL
WEAVIATE_API_KEYOptionalWeaviate API key for authentication
4
Verify it works
Restart VS Code. Weaviate MCP should appear in your MCP server list with 11 tools available.
This server adds approximately 5,665 tokens to your context window for tool definitions.