Validatar Agent Kit for GitHub Copilot

Set up the Validatar Agent Kit for GitHub Copilot: agent mode in VS Code, Copilot CLI, or the Copilot cloud agent on github.com. When you finish, Copilot can explore your Validatar catalog, create and run tests, and package test packs.

Before you start

• GitHub Copilot with agent mode available to you.
• 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 GitHub Copilot from the Validatar Marketplace.
2. Extract the zip. It holds one folder, validatar-kit-copilot/. Use it as your working folder, or copy its contents into an existing repository (see below).

The kit puts the always-on instructions in .github/copilot-instructions.md and the skills in .github/skills/, which every Copilot surface reads.

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 (the helper scripts and Copilot CLI read them):

   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.

3. In the kit folder, run python validatar/scripts/setup.py configure, then python validatar/scripts/setup.py check.

VS Code (agent mode)

1. Restart VS Code, open the kit folder and trust the workspace.
2. Open .vscode/mcp.json (written by setup.py configure) and click Start above the validatar server. VS Code asks for the MCP token once and keeps it in its secret storage.
3. Open Copilot Chat, switch to Agent, and check that the tools list includes the validatar tools.
4. Ask: "Connect to Validatar and tell me what projects and data sources I have."

VS Code asks before the agent runs a helper script in the terminal. To let read-only checks run without asking, add them to chat.tools.terminal.autoApprove in your settings, for example:

"chat.tools.terminal.autoApprove": {
  "python validatar/scripts/setup.py check": true,
  "/^python validatar\\/scripts\\/check_config\\.py /": true
}

Copilot CLI

Run copilot in the kit folder and trust the folder when asked. Copilot CLI reads .mcp.json, which takes the URL and token from VALIDATAR_URL and VALIDATAR_MCP_TOKEN. Type /mcp to see the server. For non-interactive runs (copilot -p), add --trust-folder.

Copilot cloud agent

1. Commit the kit's files to the repository.

2. In the repository settings, open Copilot > MCP servers and paste:

   {
     "mcpServers": {
       "validatar": {
         "type": "http",
         "url": "https://acme.cloud.validatar.com/core/mcp",
         "headers": { "x-val-api-token": "$COPILOT_MCP_VALIDATAR_TOKEN" },
         "tools": ["*"]
       }
     }
   }
   

3. Under Settings > Secrets and variables > Agents, add COPILOT_MCP_VALIDATAR_TOKEN (the MCP token). Only MCP servers see secrets that start with COPILOT_MCP_, so for the helper scripts also add VALIDATAR_URL and VALIDATAR_MCP_TOKEN (and VALIDATAR_API_TOKEN for MCP + API mode).

4. Add your instance's host to the agent firewall's custom allowlist so the scripts can reach it.

Use the kit in an existing repository

Copy .github/copilot-instructions.md (or append its content to yours), .github/skills/validatar-*, .mcp.json and .vscode/mcp.json (or merge their validatar entries), the validatar/ folder and the lines from .gitignore.

Troubleshooting