Set up Pinecone MCP in Cursor
Search Pinecone documentation, manage vector indexes, upsert data, query for relevant information, and rerank results from your AI editor.
1
Locate the config file
Cursor reads MCP server configuration from the following file:
.cursor/mcp.jsonCreate this file if it does not already exist.
2
Add the configuration
Add the following to your Cursor config file:
json
{
"mcpServers": {
"pinecone-mcp": {
"command": "npx",
"args": [
"-y",
"@pinecone-database/mcp"
],
"env": {
"PINECONE_API_KEY": "YOUR_PINECONE_API_KEY"
}
}
}
}3
Set up environment variables
Pinecone MCP requires the following environment variables:
PINECONE_API_KEYRequiredPinecone API key for authentication
4
Verify it works
Restart Cursor. Pinecone MCP should appear in your MCP server list with 7 tools available.
This server adds approximately 3,605 tokens to your context window for tool definitions.