# edit_image

Edit an existing image based on a text prompt

Agent View of the PolicyLayer registry record for `edit_image`. HTML page: https://policylayer.com/tools/aeven-ai-mcp-nanobanana/edit-image

## Facts

- Tool: `edit_image`
- Server: Nano Banana (`aeven-ai/mcp-nanobanana`) — https://policylayer.com/tools/aeven-ai-mcp-nanobanana.md
- Homepage: https://github.com/Aeven-AI/mcp-nanobanana
- Risk category: Write (Medium risk)
- Registry record: grade B, 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": "edit_image",
    "arguments": {}
  }
}
```

## Why edit_image is rated Medium

This tool modifies existing image data reversibly (the original file can typically be retained, and edits are non-destructive in the sense that the operation does not delete the underlying asset). It qualifies as Write rather than Execute because the primary action is data modification, not arbitrary code execution or external system invocation.

From the tool's own definition: "Tool description states 'Edit an existing image' — modifies existing visual data based on text prompts. The sibling tools (generate_image, generate_icon, etc.) all perform generative/creative operations, and edit_image is distinct in that it transforms rather…"

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Nano Banana (7)

- `hello` — Other — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/hello.md
- `generate_diagram` — Write — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/generate-diagram.md
- `generate_icon` — Write — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/generate-icon.md
- `generate_image` — Write — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/generate-image.md
- `generate_pattern` — Write — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/generate-pattern.md
- `generate_story` — Write — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/generate-story.md
- `restore_image` — Write — https://policylayer.com/tools/aeven-ai-mcp-nanobanana/restore-image.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=aeven-ai-mcp-nanobanana · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aeven-ai-mcp-nanobanana