How do I install the Nanobanana Restore skill?

Run npx skillmds add tools-only/nanobanana-restore in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Nanobanana Restore safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Nanobanana Restore?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Nanobanana Restore free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Nanobanana Restore?

tools-only (@tools-only) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Nanobanana Restore by tools-only — Agent Skill

Name: Nanobanana Restore
Rating: 4.2 (5 reviews)
Author: tools-only

Nanobanana Restore

Restore or enhance an existing image using the Nano Banana MCP server. Use when the user wants to fix, repair, restore, upscale, enhance, or improve an old, damaged, blurry, or low-quality image — such as removing scratches, fixing tears, enhancing colors, improving sharpness, or denoising photos. Triggers on requests like "restore this old photo", "fix this damaged image", "enhance this picture", "improve image quality", or "upscale this photo".

tools-only 999ec0e 3 files · 4.7 KB Updated Sep 9, 2026 7 repo stars

File contents

Nano Banana - Image Restoration

Restore or enhance existing images via the mcp_nanobanana_restore_image MCP tool.

Tool Call

Use mcp_nanobanana_restore_image with these parameters:

Parameter	Type	Required	Default	Description
`prompt`	string	yes	—	Restoration/enhancement instructions
`file`	string	yes	—	Input image filename to restore
`filename`	string	no	—	Custom output filename
`resolution`	`"1K"` \| `"2K"` \| `"4K"`	no	`"1K"`	Output resolution
`parallel`	number	no	2	Parallel generation count (1–8)
`preview`	boolean	no	false	Open result in default viewer

Workflow

Identify the input image file from the user's request → file.
Extract the restoration instructions → prompt.
Map any resolution, filename, or preview preferences to the corresponding parameters.
Call mcp_nanobanana_restore_image with the assembled parameters.
Report the output file path to the user.

Examples

Remove scratches:

file: "old_family_photo.jpg"
prompt: "remove scratches and enhance clarity"

Color enhancement:

file: "faded_photo.png"
prompt: "enhance colors and repair torn edges"
preview: true

High-resolution restoration:

file: "vintage_portrait.jpg"
prompt: "restore facial details and fix discoloration"
resolution: "4K"
filename: "restored_portrait"

---name: nanobanana-restoredescription: Restore or enhance an existing image using the Nano Banana MCP server. Use when the user wants to fix, repair, restore, upscale, enhance, or improve an old, damaged, blurry, or low-quality image — such as removing scratches, fixing tears, enhancing colors, improving sharpness, or denoising photos. Triggers on requests like "restore this old photo", "fix this damaged image", "enhance this picture", "improve image quality", or "upscale this photo".--- # Nano Banana - Image Restoration Restore or enhance existing images via the `mcp_nanobanana_restore_image` MCP tool. ## Tool Call Use `mcp_nanobanana_restore_image` with these parameters: | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | `prompt` | string | **yes** | — | Restoration/enhancement instructions | | `file` | string | **yes** | — | Input image filename to restore | | `filename` | string | no | — | Custom output filename | | `resolution` | `"1K"` \| `"2K"` \| `"4K"` | no | `"1K"` | Output resolution | | `parallel` | number | no | 2 | Parallel generation count (1–8) | | `preview` | boolean | no | false | Open result in default viewer | ## Workflow 1. Identify the input image file from the user's request → `file`. 2. Extract the restoration instructions → `prompt`. 3. Map any resolution, filename, or preview preferences to the corresponding parameters. 4. Call `mcp_nanobanana_restore_image` with the assembled parameters. 5. Report the output file path to the user. ## Examples **Remove scratches:** ``` file: "old_family_photo.jpg" prompt: "remove scratches and enhance clarity" ``` **Color enhancement:** ``` file: "faded_photo.png" prompt: "enhance colors and repair torn edges" preview: true ``` **High-resolution restoration:** ``` file: "vintage_portrait.jpg" prompt: "restore facial details and fix discoloration" resolution: "4K" filename: "restored_portrait" ```

Frequently asked questions