Set up the Validatar Agent Kit in Kiro, the IDE or kiro-cli (which replaced the Amazon Q Developer CLI). When you finish, Kiro can explore your Validatar catalog, create and run tests, and package test packs.
Before you start
- Kiro installed and signed in.
- 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
- Download Validatar Agent Kit for Kiro from the Validatar Marketplace.
- Extract the zip. It holds one folder,
validatar-kit-kiro/. Use it as your working folder, or copy its contents into an existing repository (see below).
Create your tokens and set the variables
-
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.
-
Set the environment variables for your user account:
Variable Value VALIDATAR_URLYour instance address, no trailing slash VALIDATAR_MCP_TOKENThe MCP token VALIDATAR_API_TOKENThe 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:exportlines in~/.zshrcor~/.bashrc. -
In the kit folder, run
python validatar/scripts/setup.py configure, thenpython validatar/scripts/setup.py check.
Check the connection
setup.py configure wrote .kiro/settings/mcp.json with your instance address:
{
"mcpServers": {
"validatar": {
"url": "https://acme.cloud.validatar.com/core/mcp",
"headers": { "x-val-api-token": "${VALIDATAR_MCP_TOKEN}" },
"autoApprove": ["describe", "list", "..."],
"disabledTools": []
}
}
}
The read-only Validatar tools are in autoApprove; tools that create or change something still ask.
- Restart Kiro and open the kit folder (or run
kiro-cliin it). - Open the MCP panel (
/mcpin the CLI):validataris connected. - Ask: "Connect to Validatar and tell me what projects and data sources I have."
The always-on instructions are the steering file .kiro/steering/validatar.md (inclusion: always), so they sit next to any AGENTS.md you already have. Skills are in .kiro/skills/.
Let the helper scripts run
Kiro asks before running shell commands that no rule covers. To let the kit's scripts run without asking each time, add a rule to ~/.kiro/settings/permissions.yaml:
- capability: shell
match: ["python validatar/scripts/*"]
effect: allow
The rule lives in your profile, so a repository cannot grant itself permissions.
Use the kit in an existing repository
Copy .kiro/steering/validatar.md, .kiro/skills/validatar-*, .kiro/settings/mcp.json (or merge its validatar entry), the validatar/ folder and the lines from .gitignore.
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
validatar shows an error |
Kiro started before the variables were set, or VALIDATAR_URL ends with / |
Run setup.py check, fix what it reports, restart Kiro |
| MCP server answers 401 | The token is not an MCP token, or expired | Create a new MCP token and update VALIDATAR_MCP_TOKEN |
| Every script asks for approval | No shell rule for the scripts | Add the permissions rule above |
api.py answers 403 "does not have scope" |
The API token lacks a scope | Create an API-type token with the scopes listed above |
| A template test has no child tests | Template tests create child tests only when materialized | Ask the agent to materialize it (MCP + API), or click Materialize Child Tests on the template |