Skip to main content

AI tools

Skills​

SVAR skills work with AI coding agents that support the SKILL.md convention, including Claude Code, Cursor, OpenAI Codex CLI, and Gemini CLI.

Run the following command to install the skill:

npx skills add svar-widgets/skills --skill svar-react

You can also download the skill folder manually from the skills repository.

Using skills​

Skills load automatically when the agent decides they match the task. To force a skill, invoke it explicitly:

  • In Claude Code: start your prompt with /svar-react
  • In OpenAI Codex CLI: start your prompt with $svar-react

Flat context files for other tools​

If you use tools without native skill support, like ChatGPT, GitHub Copilot, or browser-based playgrounds, the guides folder provides the same context as plain markdown files you can paste or attach:

  • svar-react-editor.md - context for the editor package
  • svar-react-all.md - context for all packages in one file

MCP​

The SVAR Model Context Protocol (MCP) server connects your AI assistant directly to the latest documentation and code examples.

LLMs have training-data cutoff dates, so they often miss recent features, API changes, or current best practices. The MCP server closes that gap. It provides:

  • Fresh documentation: real-time access to the latest docs.
  • RAG-based answers: a Retrieval-Augmented Generation solution that finds relevant docs and generates precise code snippets for your query.

Once enabled, your AI agent queries the server for help, so the code it generates stays accurate and up to date.

Server URL: https://docs.svar.dev/mcp

Hosted service​

The MCP server is hosted and ready to use-there is nothing to install or run locally. Add the server URL to your AI tool to get started.

We do not collect or store information that identifies you. We may store anonymized queries to debug and improve the service.

Integration guides​

Use these steps to enable the SVAR MCP server in popular AI coding tools.

Claude Code​

Add the server with the Claude Code CLI:

claude mcp add --transport http svar-mcp https://docs.svar.dev/mcp

You can also add it manually to your ~/.claude.json or .mcp.json configuration file:

{
	"mcpServers": {
		"svar-mcp": {
			"type": "http",
			"url": "https://docs.svar.dev/mcp"
		}
	}
}

For more details, see the official documentation.

OpenAI Codex​

Add the server with the Codex CLI:

codex mcp add svar-mcp --url https://docs.svar.dev/mcp

You can also add it manually to the global ~/.codex/config.toml file or a project-level .codex/config.toml file:

[mcp_servers.svar-mcp]
url = "https://docs.svar.dev/mcp"

Run codex mcp list to verify the configuration. In the Codex terminal UI, use /mcp to view the active servers.

For more details, see the official documentation.

Cursor​

Cursor has built-in support for MCP servers.

  1. Open Cursor Settings (Cmd+Shift+J or Ctrl+Shift+J).
  2. Navigate to Tools & MCP.
  3. Click Add Custom MCP.
  4. Enter the server configuration:
{
  "mcpServers": {
    "svar-mcp": {
      "url": "https://docs.svar.dev/mcp"
    }
  }
}

Once added, reference it in your chats (e.g., "Check SVAR Docs for how to configure the editor").

You can also install the SVAR MCP server directly in Cursor with one click:

Install MCP for Cursor

Learn more in the official documentation.

VS Code​

Click the button to install the SVAR MCP server directly in VS Code:

Install MCP for VS Code

Google Antigravity​

Antigravity 2.0​

info

Refer to the official documentation for more guidance.

Follow the steps:

  1. Open the command palette and type "mcp add".
  2. Select "HTTP".
  3. Enter the URL https://docs.svar.dev/mcp.
  4. Enter the Name svar-mcp.

Antigravity CLI​

info

Check the related guide to learn about migration from Gemini CLI to Antigravity CLI.

To use the server with the Antigravity CLI tool:

agy mcp add --transport http svar-mcp https://docs.svar.dev/mcp

You can also configure it manually:

  1. Create your MCP configuration file in one of these locations:
    • Global: ~/.gemini/config/mcp_config.json
    • Workspace: .agents/mcp_config.json
  2. Add the server to the mcpServers object:
{
	"mcpServers": {
		"svar-mcp": {
			"serverUrl": "https://docs.svar.dev/mcp"
		}
	}
}
  1. Run agy in the terminal.

Other IDEs / Tools​

  1. Check the settings for Model Context Protocol or Context Sources.
  2. Add a new custom source with the URL https://docs.svar.dev/mcp.

ChatGPT​

To enable the server in ChatGPT:

  1. Open ChatGPT and navigate to Settings / Apps & Connectors.
  2. Click Advanced settings.
  3. Enable Developer mode.
  4. Go "Back". The "Connectors" screen now shows a "Create" button - click it.
  5. Enter the Name svar-mcp.
  6. Enter the URL https://docs.svar.dev/mcp.
  7. Select No authentication as Authentication.
  8. Click Create to finish.

You can now ask your Custom GPT to "Consult the SVAR MCP server" when asking questions about React Editor.

Full setup details are available in the official documentation.