# create_test_run

Create a test run in a project. Description supports markdown.

Agent View of the PolicyLayer registry record for `create_test_run`. HTML page: https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/create-test-run

## Facts

- Tool: `create_test_run`
- Server: Huly (`@firfi/huly-mcp`) — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp.md
- Install: `npx -y @firfi/huly-mcp`
- Homepage: https://github.com/dearlordylord/huly-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_test_run",
    "arguments": {}
  }
}
```

## Why create_test_run is rated Medium

This tool creates a new test run resource, which is a reversible Write operation. It does not delete, execute arbitrary code, or move money. The 'medium' severity reflects that an AI agent creating unauthorized or malformed test runs could clutter project data or interfere with testing workflows, but the operation is not destructive or irreversible.

From the tool's own definition: "Tool name 'create_test_run' and description 'Create a test run in a project' indicate creation of new data in a project management/testing context."

## Use case

AI agents use create_test_run to create or update resources in Huly, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Huly environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Huly:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_test_run": {
      "limits": [
        {
          "counter": "create_test_run_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Huly (517)

- `cancel_approval_request` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/cancel-approval-request.md
- `cancel_execution` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/cancel-execution.md
- `delete_activity_reply` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-activity-reply.md
- `delete_association` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-association.md
- `delete_attachment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-attachment.md
- `delete_board_card` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-board-card.md
- `delete_board_label` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-board-label.md
- `delete_card` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-card.md
- `delete_card_comment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-card-comment.md
- `delete_channel` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-channel.md
- `delete_channel_message` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-channel-message.md
- `delete_chat_message_attachment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-chat-message-attachment.md
- `delete_class_collaborator_metadata` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-class-collaborator-metadata.md
- `delete_comment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-comment.md
- `delete_component` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-component.md
- `delete_dm_message` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-dm-message.md
- `delete_document` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-document.md
- `delete_drawing` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-drawing.md
- `delete_drive` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-drive.md
- `delete_drive_file_comment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-drive-file-comment.md
- `delete_drive_item` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-drive-item.md
- `delete_event` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-event.md
- `delete_huly_attribute` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-huly-attribute.md
- `delete_huly_enum` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-huly-enum.md
- `delete_huly_permission` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-huly-permission.md
- `delete_huly_sequence` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-huly-sequence.md
- `delete_inventory_category` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-inventory-category.md
- `delete_inventory_product` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-inventory-product.md
- `delete_inventory_product_attachment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-inventory-product-attachment.md
- `delete_inventory_product_comment` — Destructive — https://policylayer.com/tools/io-github-dearlordylord-huly-mcp/delete-inventory-product-comment.md
- …and 487 more: https://policylayer.com/tools/io-github-dearlordylord-huly-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-dearlordylord-huly-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dearlordylord-huly-mcp