Image Generation tools in Cogny
Cogny's Image Generation integration exposes 9 tools (4 read, 5 write) to an AI agent over MCP. The same tools are available on every plan, from your own AI client or inside the Cogny app.
Built in for every workspace: there is nothing to connect.
- Read (4): only reads data.
- Write (5): creates or changes something.
- Destructive (0): deletes, removes or replaces something.
Over MCP your own AI client asks before it runs a write. To take a tool away from your agent, block it in Settings → Integrations. Plans, approvals and limits.
All tools
| Tool | Kind | What it does |
|---|---|---|
tool_generate_image | Write | Generate an image using AI (Google Gemini / Nano Banana 2). |
tool_generate_image_openai | Write | Generate an image with OpenAI GPT Image — the alternative to generate_image (Nano Banana). |
tool_generate_video | Write | Submit a Veo 3.1 video generation request (non-blocking). |
tool_check_video_generation | Read | Check the status of a Veo video generation operation. |
tool_list_brand_assets | Read | List brand assets uploaded for this warehouse. |
tool_request_upload_url | Write | Mint a single-use upload URL for the curl-driven upload flow. |
tool_upload_file | Write | Upload a file and get a public URL. |
tool_analyze_media | Read | Analyze a video or image using Google Gemini's multimodal AI. |
tool_list_uploads | Read | List files previously uploaded via upload_file. |
Exact input schemas come from tools/list once Image Generation is connected; the free plan is enough to check. Missing something? Your agent can ask for it with request_feature.