{
  "markdown": "# Pinecone Gemini CLI Extension\n\nThe official Pinecone extension for the Gemini CLI. Manage vector indexes, perform semantic search, and build document Q&A assistants directly from your terminal using AI-powered Agent Skills and MCP tools.\n\n## Quick Start\n\n```bash\n# 1. Install the extension\ngemini extensions install https://github.com/pinecone-io/gemini-cli-extension\n\n# 2. Set your API key (get one free at https://app.pinecone.io)\nexport PINECONE_API_KEY=\"your-api-key\"\n\n# 3. Restart Gemini CLI, then ask:\n#    \"Use the quickstart skill to help me get started with Pinecone\"\n```\n\n> **Note:** 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.\n\n## Installation\n\n### 1. Prerequisites\n- **Pinecone Account:** Create a free account at [app.pinecone.io](https://app.pinecone.io/?sessionType=signup).\n- **Pinecone API Key:** Generate a key in the Pinecone console.\n- **uv (Recommended):** To run the Python scripts bundled with the skills, [install uv](https://docs.astral.sh/uv/getting-started/installation/).\n- **Pinecone CLI (Optional):** For advanced vector management, install the CLI:\n  ```bash\n  brew tap pinecone-io/tap\n  brew install pinecone-io/tap/pinecone\n  ```\n\n### 2. Add the Extension\n```bash\ngemini extensions install https://github.com/pinecone-io/gemini-cli-extension\n```\n\n### 3. Configure the API Key\nYou must set your Pinecone API key in two places to unlock all features:\n\n1. **MCP Configuration:** Add your key to the `PINECONE_API_KEY` setting in your Gemini CLI or MCP server configuration.\n2. **Environment Variable:** Export the key in your terminal so the bundled skill scripts can access it:\n   ```bash\n   export PINECONE_API_KEY=\"your-api-key\"\n   ```\n\n## Usage\n\n### Agent Skills\nThis extension includes specialized **Agent Skills** that are automatically invoked based on your conversation. You don't need to memorize commands; just state your intent:\n\n- *\"Show me the Pinecone quickstart\"*\n- *\"Create a document assistant from these files\"*\n- *\"Search my 'products' index for 'green shoes'\"*\n- *\"How do I manage namespaces with the Pinecone CLI?\"*\n\n**Note on Auto-Invocation:** If you find the agent isn't picking up a specific skill, you can explicitly ask for it by name: *\"Use the `quickstart` skill to help me get started.\"*\n\n### Available Skills\n| Skill | Best Used For... |\n|---|---|\n| `quickstart` | Getting started with vector databases or document assistants. |\n| `query` | Semantic text search on integrated indexes via MCP. |\n| `assistant` | RAG-based document Q&A with citations. |\n| `cli` | Learning and running `pc` terminal commands. |\n| `mcp` | Reference for all available Pinecone MCP tools. |\n| `pinecone-docs` | Looking up official documentation and API references. |\n| `help` | Overview of all setup requirements and skills. |\n\n### MCP Tools\nThe extension also provides direct access to Pinecone MCP tools for low-level operations like `list-indexes`, `describe-index`, and `search-records`.\n\n## Troubleshooting\n\n- **API Key Errors:** If a skill script fails, ensure you have exported `PINECONE_API_KEY` in your current terminal session.\n- **Skill Activation:** If the agent is improvising instead of using a skill, try saying *\"Activate the [skill-name] skill\"*.\n- **Documentation:** Use the `pinecone-docs` skill or visit [docs.pinecone.io](https://docs.pinecone.io) for help.\n\n## Contributing\n\nWe welcome contributions! Please see [CONTRIBUTING.md](./CONTRIBUTING.md) for details on how to report issues or submit improvements.\n\n## License\n\nMIT\n",
  "bytes": 3628,
  "sha": "259fa10fe9a80afa87b122e3cf9ff7f1638944e069de035b6005b8df4f436d09",
  "repo_slug": "pinecone-io/gemini-cli-extension",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_pinecone_io_gemini_cli_extension_95f83861/readme"
}