PluginBench
MCP Server
Active
MIT

io.github.getjoystick/nanobanana-mcp MCP Server

io.github.getjoystick/nanobanana-mcp

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.getjoystick/nanobanana-mcp MCP server?

Lean MCP server for Google's Nano Banana (Gemini) image models. Returns file paths, not base64.

How to install io.github.getjoystick/nanobanana-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • GEMINI_API_KEY
    required
    secret

    Gemini API key from https://aistudio.google.com/apikey

  • NANOBANANA_MODEL

    Default image model override (default: gemini-3.1-flash-image)

  • NANOBANANA_OUTPUT_DIR

    Default output directory override

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "nanobanana-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@nanobanana/mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "NANOBANANA_MODEL": "<YOUR_NANOBANANA_MODEL>",
        "NANOBANANA_OUTPUT_DIR": "<YOUR_NANOBANANA_OUTPUT_DIR>"
      }
    }
  }
}

Related MCP servers

Runtime governance, proof, outcome closure, and fleet intelligence for MCP-compatible AI agents.

5
JavaScript
MIT
View repository →

6 hydration calculators for LLMs: water intake, dehydration, pregnancy, CKD, athlete, energy.

0
JavaScript
MIT
View repository →
COCorent logo

Corent

Maintained

Generate images, videos, voice, and text via the Corent API. Auto model routing with fallback.

0
TypeScript
MIT
View repository →
HAhaiku.rag logo

haiku.rag

Active

Local-first agentic RAG with hybrid search, reranking, and multimodal document retrieval with citations.

581
Python
MIT
View repository →

Provides tools to use MASV API. MASV is reliable and secure large file transfer service.

5
TypeScript
MIT
View repository →
MCmcpm logo

mcpm

Active

MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

2
TypeScript
MIT
View repository →