# generate_image

Generate images from text prompts using Kling AI. Create high-quality images with multiple aspect ratios and optional character reference support. Supports models v1, v1.5, and v2 with customizable parameters for creative control.

Agent View of the PolicyLayer registry record for `generate_image`. HTML page: https://policylayer.com/tools/199-mcp-mcp-kling/generate-image

## Facts

- Tool: `generate_image`
- Server: MCP Kling (`199-mcp/mcp-kling`) — https://policylayer.com/tools/199-mcp-mcp-kling.md
- Homepage: https://github.com/199-mcp/mcp-kling
- Risk category: Execute (High risk)
- Registry record: grade D, 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": "generate_image",
    "arguments": {}
  }
}
```

## Why generate_image is rated High

This tool triggers an external AI image generation operation via Kling AI's service. It is not a simple data write (no local data is created/modified by the caller) but rather executes an external operation whose effects depend on the arguments (prompt, model, parameters). It falls under Execute as it invokes an external computation/generation pipeline.

From the tool's own definition: "Generate images from text prompts using Kling AI... Supports models v1, v1.5, and v2 with customizable parameters"

## Use case

AI agents invoke generate_image to trigger actions in MCP Kling. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_image": {
      "limits": [
        {
          "counter": "generate_image_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on MCP Kling (11)

- `create_lipsync` — Execute — https://policylayer.com/tools/199-mcp-mcp-kling/create-lipsync.md
- `generate_image_to_video` — Execute — https://policylayer.com/tools/199-mcp-mcp-kling/generate-image-to-video.md
- `virtual_try_on` — Execute — https://policylayer.com/tools/199-mcp-mcp-kling/virtual-try-on.md
- `generate_video` — Financial — https://policylayer.com/tools/199-mcp-mcp-kling/generate-video.md
- `check_image_status` — Read — https://policylayer.com/tools/199-mcp-mcp-kling/check-image-status.md
- `check_video_status` — Read — https://policylayer.com/tools/199-mcp-mcp-kling/check-video-status.md
- `get_account_balance` — Read — https://policylayer.com/tools/199-mcp-mcp-kling/get-account-balance.md
- `get_resource_packages` — Read — https://policylayer.com/tools/199-mcp-mcp-kling/get-resource-packages.md
- `list_tasks` — Read — https://policylayer.com/tools/199-mcp-mcp-kling/list-tasks.md
- `apply_video_effect` — Write — https://policylayer.com/tools/199-mcp-mcp-kling/apply-video-effect.md
- `extend_video` — Write — https://policylayer.com/tools/199-mcp-mcp-kling/extend-video.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=199-mcp-mcp-kling · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/199-mcp-mcp-kling