GENERATE OR EDIT IMAGES - Create images from text prompts or edit existing images using Gemini image models. CAPABILITIES: Text-to-image generation, image editing with instructions, multiple image generation (1-4 images), configurable aspect ratios. MODELS: gemini-3-pro-image-preview (default, wi...
AI agents invoke generate_images to trigger actions in Gemini MCP Server. 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.
This tool executes an external AI model inference operation (image generation/editing) and writes output files to disk. It triggers external operations (Gemini API calls) and has file system side effects (auto-saving images). The most severe applicable category is Execute, as it runs external operations with effects depending on arguments (prompt, model, input image).
From the tool's definition GENERATE OR EDIT IMAGES - Create images from text prompts or edit existing images using Gemini image models... Images auto-saved to outputDir
Attacks that exploit this kind of access
GENERATE OR EDIT IMAGES - Create images from text prompts or edit existing images using Gemini image models. CAPABILITIES: Text-to-image generation, image editing with instructions, multiple image generation (1-4 images), configurable aspect ratios. MODELS: gemini-3-pro-image-preview (default, with thinking support) or gemini-2.5-flash-image (faster). WORKFLOW: 1) Provide text prompt, 2) Optionally specify model, aspect ratio, and number of images, 3) For editing: provide inputImageUri from uploaded file, 4) Images auto-saved to outputDir. RETURNS: Array of generated images with file paths. COST: ~1,290 tokens per image. All images include SynthID watermark. It is categorised as a Execute tool in the Gemini MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gemini MCP Server MCP server in PolicyLayer and add a rule for generate_images: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gemini MCP Server. Nothing to install.
generate_images is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the generate_images rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for generate_images. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
generate_images is provided by the Gemini MCP Server MCP server (mintmcqueen/gemini-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →