Skip to main content
Glama
Jolyland

Nano Banana Pro AI MCP Server

by Jolyland
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin

Nano Banana Pro AI MCP Server

Nano Banana Pro AI Image Editor Free Online by Gemini AI

MCP Badge Node Zero Config License: MIT Read Only Stdio Transport MCP

A Model Context Protocol server that exposes the canonical Nano Banana Pro AI knowledge surface — image generation workflows and styles, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.

Official website: https://nanobanana-ai.online

🎨 About Nano Banana Pro AI

Nano Banana Pro AI is an online image and video editing platform that uses multiple AI models to handle visual tasks that would otherwise require dedicated design software or manual effort. Users can generate images from text prompts, remove or swap backgrounds, erase unwanted objects, enhance photo quality, and convert still images into short video clips — all through a browser-based interface. The platform draws on models including Flux, GPT Image, Ideogram, and Kling, and covers more than 60 specialized tools across image and video workflows. New accounts receive 55 free credits with no watermarks on outputs, making it straightforward to evaluate before committing to a paid plan.

Related MCP server: aiphotoeditor-mcp

Key Features

  • Text-to-image generation using multiple AI models (Flux, GPT Image, Ideogram, and others), with results delivered in 5 to 30 seconds

  • Background removal and replacement with AI-assisted precision, supporting JPG, PNG, and WEBP uploads

  • Smart object removal that fills in the erased area to produce a clean, natural result

  • Image-to-video conversion that animates a still photo into an MP4 clip, typically within one to five minutes

  • Batch processing for applying consistent edits across multiple images in a single pass

  • AI photo enhancement covering quality upscaling, lighting correction, and color grading, with output up to 4K resolution

Use Cases

  • An e-commerce seller shoots product photos on a cluttered table and uses background removal plus replacement to produce clean, studio-style listings

  • A social media manager generates on-brand visuals from text prompts rather than sourcing stock photography or briefing a designer

  • A photographer uses the batch enhancement tool to apply consistent color grading across an entire shoot before delivery

  • A marketer animates a product image into a short video clip for use in ads without commissioning video production

  • A small business owner removes distracting elements from existing brand photos without reopening the original files in editing software

Who Is It For

Nano Banana Pro AI is built for people who need professional-looking visual content but do not have the time, budget, or training to work with traditional editing software. E-commerce sellers and product photographers will find the background tools and batch workflows particularly practical. Marketing teams and content creators benefit from fast text-to-image generation and the ability to animate stills into video. The credit-based pricing model keeps entry costs low for occasional users, while paid plans that include commercial usage rights suit agencies and businesses producing content at scale. No prior design experience is required to use any of the tools.

Tools

list_styles

Return the canonical list of image-generation styles or presets the site exposes. (Nano Banana Pro AI)

Input: no parameters. Returns: text/markdown.

get_pricing

Return the canonical pricing entry point for Nano Banana Pro AI.

Input: no parameters. Returns: text/markdown.

get_official_links

Return the canonical list of official links for Nano Banana Pro AI (website, support, docs when available).

Input: no parameters. Returns: text/markdown.

Resources

  • site://nanobanana/styles — Supported image-generation styles and presets.

  • site://nanobanana/pricing — Canonical pricing entry point.

  • site://nanobanana/faq — Short FAQ generated from public site metadata.

  • site://nanobanana/links — Canonical URLs to share with users.

Prompts

tell_me_about_nanobanana

Summarize what the site is, who it's for, and how it works. — Nano Banana Pro AI

try_image_style_nanobanana

Recommend a starting image-generation style for a stated goal. — Nano Banana Pro AI

Installation

Install via Smithery

npx -y @smithery/cli install nanobanana-mcp --client claude

(Replace claude with cursor, windsurf, or continue for those clients.)

Install from source

git clone https://github.com/rocnubie/nanobanana-mcp.git
cd nanobanana-mcp
pnpm install

Then add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):

{
  "mcpServers": {
    "nanobanana-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/nanobanana-mcp/src/index.mjs"
      ]
    }
  }
}

Debug with MCP Inspector

npx @modelcontextprotocol/inspector node src/index.mjs

Official Links

Development

pnpm install
pnpm start                 # run the server over stdio

License

MIT

Available Tools

3 tools
get_pricingB

Return the canonical pricing entry point for Nano Banana Pro AI.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose behavioral traits such as read-only status, authentication requirements, or the nature of the returned 'pricing entry point'. This is a minimal description that leaves the agent to infer safety and output behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. It is appropriately sized for a tool with no parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters), the description is nearly sufficient, but it lacks clarity on what the 'pricing entry point' actually returns (e.g., a URL, an object, a price list). With no output schema, the description should provide this context but does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the schema is trivially complete (100% coverage). The description does not need to explain parameters; the lack of parameters is self-evident from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Return') and the resource ('the canonical pricing entry point'), and specifies the product ('Nano Banana Pro AI'). This makes it distinct from sibling tools like list_styles and get_official_links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than explicit: the tool is evidently meant for retrieving pricing information. However, there is no explicit guidance on when to use it vs. alternatives, nor any exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_stylesA

Return the canonical list of image-generation styles or presets the site exposes. (Nano Banana Pro AI)

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It indicates a read operation by using 'Return', but does not disclose behavior like whether the list is static, locale-dependent, or requires authentication. For a simple list tool this is acceptable but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately conveys the tool's purpose. No wasted words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is very simple (no parameters, no output schema). The description tells the agent it returns a list of styles/presets, which is sufficient for this scope. It could mention the return format, but not necessary for a list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the input schema trivially covers everything. The description adds no parameter-specific details, but none are needed. Baseline 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb ('Return') and resource ('canonical list of image-generation styles or presets'). It distinguishes itself from siblings by focusing on styles/presets rather than pricing or links.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The purpose implies when to use it (when you need the list of styles/presets). It does not explicitly discuss alternatives or exclusions, but the sibling tools are clearly unrelated, so the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv0.1.0
    • First observedget_official_links
    • First observedget_pricing
    • First observedlist_styles
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

Each tool returns a distinct category of information: styles, pricing, and links. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: list_styles, get_pricing, get_official_links. While list and get are different verbs, they are both standard and used appropriately for the action.

Tool Count5/5

With 3 tools, the server is well-scoped for its purpose of providing canonical info about Nano Banana Pro AI. Each tool earns its place and the count is within the ideal range.

Completeness5/5

For an informational server, the surface covers the key facts users would need: style presets, pricing, and official links. No obvious gaps are apparent for the intended domain.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jolyland/nanobanana-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server