High-risk tools in Open Google Image Generator MCP
10 of the 19 tools in Open Google Image Generator MCP are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
tool_batch_generateExecuteGenerate images for multiple prompts in a single call (max 10, max 4 concurrent).
-
tool_extend_videoExecuteExtend an existing video by generating additional seconds at the end.
-
tool_generate_imageExecuteGenerate an image from a text prompt using Vertex AI Imagen or Gemini.
-
tool_generate_musicExecuteGenerate music from a text prompt using Lyria. Check tool_list_available_models to verify Lyria is enabled in your project.
-
tool_generate_speechExecuteConvert text to speech using Gemini TTS. Returns a WAV file path in outputs/.
-
tool_image_to_videoExecuteGenerate a video from a still image as the first frame using Veo.
-
tool_live_generateExecuteGenerate text using Gemini streaming. The full streamed response is accumulated and returned.
-
tool_run_pipelineExecuteChain image processing steps sequentially. Each step's output becomes the next step's input.
-
tool_transform_imageExecuteFree-form 'image + text -> image' transformation via Gemini multimodal models.
-
tool_video_object_editExecuteInsert or remove an object in a video using Veo.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.