Validatar Agent Kit for Google Antigravity

Set up the Validatar Agent Kit in Google Antigravity: the Antigravity IDE or the agy CLI. The same kit works in Gemini CLI for Gemini Code Assist Standard and Enterprise users. When you finish, the agent can explore your Validatar catalog, create and run tests, and package test packs.

Before you start

• Google Antigravity installed and signed in (or Gemini CLI).
• Python 3.9 or newer on the PATH (python --version).
• Your Validatar instance address, for example https://acme.cloud.validatar.com.
• A Validatar user that can create tests in at least one project, ideally a sandbox project.

Get the kit

1. Download Validatar Agent Kit for Google Antigravity from the Validatar Marketplace.
2. Extract the zip. It holds one folder, validatar-kit-antigravity/. Use it as your working folder, or copy its contents into an existing repository (see below).

Create your tokens and set the variables

1. In Validatar, open your user profile, User Tokens. Create a token of type MCP. For MCP + API mode (optional), also create a token of type API with the scopes Authoring, Execution, Data Steward and Catalog.

2. Set the environment variables for your user account:

   Variable	Value
   VALIDATAR_URL	Your instance address, no trailing slash
   VALIDATAR_MCP_TOKEN	The MCP token
   VALIDATAR_API_TOKEN	The API token (optional: MCP + API mode)

   Windows (PowerShell): setx VALIDATAR_URL "https://acme.cloud.validatar.com", and the same for each token. macOS or Linux: export lines in ~/.zshrc or ~/.bashrc.

Add the MCP server

Antigravity keeps MCP servers in your user profile. In the kit folder, run:

python validatar/scripts/setup.py configure --user

It adds this entry to ~/.gemini/config/mcp_config.json and backs up the file first:

{
  "mcpServers": {
    "validatar": {
      "serverUrl": "https://acme.cloud.validatar.com/core/mcp",
      "headers": { "x-val-api-token": "${VALIDATAR_MCP_TOKEN}" },
      "timeoutSeconds": 600
    }
  }
}

Note: Antigravity's documentation does not say whether it expands environment variables in MCP headers. If the server answers 401, open ~/.gemini/config/mcp_config.json and replace ${VALIDATAR_MCP_TOKEN} with the token itself. That file is in your user profile, not in the kit folder, so the token stays out of your repository.

Then run python validatar/scripts/setup.py check.

Start Antigravity

1. Restart Antigravity and open the kit folder (or run agy in it).
2. Check the MCP panel (/mcp in agy): validatar is connected.
3. Ask: "Connect to Validatar and tell me what projects and data sources I have."

The always-on instructions are in AGENTS.md and the skills in .agents/skills/. Antigravity asks before running shell commands. To let the kit's helper scripts run without asking, add "command(python)" to permissions.allow in your Antigravity settings.

Gemini CLI

setup.py configure also writes .gemini/settings.json in the kit folder. It tells Gemini CLI to read AGENTS.md (Gemini CLI reads only GEMINI.md by default) and connects the validatar server, reading the token from ${VALIDATAR_MCP_TOKEN}:

{
  "context": { "fileName": ["AGENTS.md"] },
  "mcpServers": {
    "validatar": {
      "httpUrl": "https://acme.cloud.validatar.com/core/mcp",
      "headers": { "x-val-api-token": "${VALIDATAR_MCP_TOKEN}" },
      "timeout": 600000
    }
  }
}

Run gemini in the kit folder and check /mcp. Skills are read from .agents/skills/.

Use the kit in an existing repository

Copy AGENTS.md (or append its content to yours), .agents/skills/validatar-*, the validatar/ folder, .gemini/settings.json if you use Gemini CLI (or merge its entries), and the lines from .gitignore.

Troubleshooting