Features
- 8 built-in skills for index management, semantic search, full-text search, assistant creation, and more
- Bundled MCP server (
@pinecone-database/mcp) for direct Pinecone operations from Cursor Agent - Slash commands like
/pinecone-quickstartand/pinecone-queryfor quick access - Natural language activation β Cursor Agent invokes the right skill automatically based on your conversation
Prerequisites
- A Pinecone API key
- Cursor installed
- Node.js v18+ (required for the bundled MCP server)
- uv installed (optional, runs bundled Python scripts)
- Pinecone CLI installed (optional, enables the
pinecone-cliskill)
Installation
Set your API key
Add your Pinecone API key to a Cursor loads this file into the MCP server via its
.env file at your workspace root:envFile field, so you donβt need to export the key in your shell.Install the plugin
Available skills
| Skill | Command | Description |
|---|---|---|
| Help | /pinecone-help | Overview of all skills and setup requirements. |
| Quickstart | /pinecone-quickstart | Interactive onboarding β create an index, upsert data, and query. Choose between a Database path or Assistant path. |
| Query | /pinecone-query | Search integrated indexes using natural language via the Pinecone MCP server. |
| Assistant | /pinecone-assistant | Create, upload, sync, and chat with Pinecone Assistants for document Q&A with citations. |
| CLI | /pinecone-cli | Guide for using the Pinecone CLI (pc) from the terminal. |
| Full-text search | /pinecone-full-text-search | Create, ingest into, and query a Pinecone full-text-search (FTS) index using the preview API. |
| MCP | /pinecone-mcp | Reference for all Pinecone MCP server tools. |
| Docs | /pinecone-docs | Curated links to official Pinecone documentation. |
MCP tools
The plugin includes the Pinecone MCP server, which provides the following tools:search-docsβ Search the official Pinecone documentation.list-indexesβ List all available Pinecone indexes.describe-indexβ Get index configuration and namespaces.describe-index-statsβ Get record counts and namespace statistics.create-index-for-modelβ Create a new index with integrated embeddings.upsert-recordsβ Insert or update records in an index.search-recordsβ Search records with optional metadata filtering and reranking.cascading-searchβ Search across multiple indexes with deduplication and reranking.rerank-documentsβ Rerank documents using a specified reranking model.