search-docs
: Search the official Pinecone documentation.list-indexes
: Lists all Pinecone indexes.describe-index
: Describes the configuration of an index.describe-index-stats
: Provides statistics about the data in the index, including the number of records and available namespaces.create-index-for-model
: Creates a new index that uses an integrated inference model to embed text as vectors.upsert-records
: Inserts or updates records in an index with integrated inference.search-records
: Searches for records in an index based on a text query, using integrated inference for embedding. Has options for metadata filtering and reranking.cascading-search
: Searches for records across multiple indexes, deduplicating and reranking the results.rerank-documents
: Reranks a collection of records or text documents using a specialized reranking model.node
and npx
available on your PATH
Add the MCP server
.cursor/mcp.json
file, if it doesn’t exist, and add the following configuration:YOUR_API_KEY
with your Pinecone API key.Check the status
Add Pinecone rules
.cursor/rules/pinecone.mdc
file and add the following:Test the server
Command + i
to open the Agent chat. Test the Pinecone MCP server with prompts that required the server to generate Pinceone-compatible code and perform tasks in your Pinecone account.Generate code:Write a Python script that creates a dense index with integrated embedding, upserts 20 sentences about dogs, waits 10 seconds, searches the index, and reranks the results.Perform tasks:
Create a dense index with integrated embedding, upsert 20 sentences about dogs, waits 10 seconds, search the index, and reranks the results.
Add the MCP server
YOUR_API_KEY
with your Pinecone API key.Check the status
Test the server
Write a Python script that creates a dense index with integrated embedding, upserts 20 sentences about dogs, waits 10 seconds, searches the index, and reranks the results.Perform tasks:
Create a dense index with integrated embedding, upsert 20 sentences about dogs, waits 10 seconds, search the index, and reranks the results.
Add the MCP server
YOUR_API_KEY
with your Pinecone API key.Check the status
/mcp
command to check the status of the Pinecone MCP. You should see the following:Test the server
Write a Python script that creates a dense index with integrated embedding, upserts 20 sentences about dogs, waits 10 seconds, searches the index, and reranks the results.Perform tasks:
Create a dense index with integrated embedding, upsert 20 sentences about dogs, waits 10 seconds, search the index, and reranks the results.