Skip to main content
The official Pinecone extension for Gemini CLI provides AI-powered skills and MCP server integration directly in your terminal. Use natural language to manage indexes, query data, build RAG applications, and create document Q&A assistants.

Features

  • 7 built-in skills for index management, semantic search, assistant creation, and more
  • MCP server integration for direct Pinecone operations from Gemini CLI
  • Natural language activation — just describe what you want and the right skill is invoked automatically

Prerequisites

Installation

1

Set your API key

export PINECONE_API_KEY="YOUR_API_KEY"
Replace YOUR_API_KEY with your Pinecone API key.
2

Install the extension

gemini extensions install https://github.com/pinecone-io/gemini-cli-extension
3

Restart Gemini CLI

Restart Gemini CLI to activate the extension. Then ask:
Use the help skill to show me what Pinecone skills are available.
If you hit API key errors, exit Gemini CLI, run export PINECONE_API_KEY="your-key" in your terminal, and start Gemini CLI again. The CLI only reads environment variables at launch.

Available skills

SkillDescription
quickstartStep-by-step onboarding — create an index, upload data, and run your first search.
querySearch integrated indexes using natural language text via the Pinecone MCP.
assistantCreate, manage, and chat with Pinecone Assistants for document Q&A with citations.
cliGuide for using the Pinecone CLI from the terminal.
mcpReference for all available Pinecone MCP server tools and their parameters.
pinecone-docsCurated links to official Pinecone documentation, organized by topic.
helpOverview of all skills and what you need to get started.
Skills are activated automatically based on your conversation. If the agent doesn’t pick up a specific skill, explicitly ask for it: “Use the quickstart skill to help me get started.”

MCP tools

The extension includes the Pinecone MCP server, which provides the following tools:
  • search-docs — Search the official Pinecone documentation.
  • list-indexes — List all available Pinecone indexes.
  • describe-index — Get index configuration and namespaces.
  • describe-index-stats — Get record counts and namespace statistics.
  • create-index-for-model — Create a new index with integrated embeddings.
  • upsert-records — Insert or update records in an index.
  • search-records — Search records with optional metadata filtering and reranking.
  • cascading-search — Search across multiple indexes with deduplication and reranking.
  • rerank-documents — Rerank documents using a specified reranking model.
For full MCP server documentation, see Use the Pinecone MCP server.

Resources