Server data from the Official MCP Registry
Nano Banana MCP server backed by Polza AI media and storage APIs.
Nano Banana MCP server backed by Polza AI media and storage APIs.
Valid MCP server (0 strong, 3 medium validity signals). 8 known CVEs in dependencies (1 critical, 5 high severity) Package registry verified. Imported from the Official MCP Registry.
6 files analyzed · 9 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Unverified package source
We couldn't verify that the installable package matches the reviewed source code. Proceed with caution.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-ivanantigravity-lgtm-nanobanana-2-polzaia-mcp-server": {
"args": [
"nanobanana-2-polzaia-mcp-server"
],
"command": "uvx"
}
}
}From the project's GitHub README.
mcp-name: io.github.ivanantigravity-lgtm/nanobanana-2-polzaia-mcp-server
MCP server for image generation and editing through Polza, using:
google/gemini-3.1-flash-image-preview as the default Nano Banana 2 modelgoogle/gemini-3-pro-image-preview for higher-quality compositionsgoogle/gemini-2.5-flash-image for faster draft generationThis project exposes MCP tools like:
generate_imageupload_fileoutput_statsmaintenanceClaude Code or another MCP clientuvPython 3.11+POLZA_AI_API_KEYFor Claude Code / VS Code, the fastest setup is:
uv.mcp.json file in your project root{
"mcpServers": {
"nanobanana-polza": {
"command": "uvx",
"args": ["nanobanana-2-polzaia-mcp-server@latest"],
"env": {
"POLZA_AI_API_KEY": "your-polza-api-key-here",
"POLZA_BASE_URL": "https://polza.ai/api",
"IMAGE_OUTPUT_DIR": "/Users/yourname/Documents/nanobanana"
}
}
}
}
Then restart Claude Code / VS Code.
git clone https://github.com/ivanantigravity-lgtm/nanobanana-2-polzaia-mcp-server.git
cd nanobanana-2-polzaia-mcp-server
uv sync
cp .env.example .env
Set at minimum:
POLZA_AI_API_KEY=your_polza_api_key
POLZA_BASE_URL=https://polza.ai/api
IMAGE_OUTPUT_DIR=/absolute/path/to/output
Run locally:
uv run python -m nanobanana_mcp_server.server
If the package is published to PyPI, the easy install path is a project-level .mcp.json:
{
"mcpServers": {
"nanobanana-polza": {
"command": "uvx",
"args": ["nanobanana-2-polzaia-mcp-server@latest"],
"env": {
"POLZA_AI_API_KEY": "your-polza-api-key-here",
"POLZA_BASE_URL": "https://polza.ai/api",
"IMAGE_OUTPUT_DIR": "/Users/demo/Documents/nanobanana"
}
}
}
}
If the user runs from source instead of a published package:
{
"mcpServers": {
"nanobanana-polza-local": {
"command": "uv",
"args": ["run", "python", "-m", "nanobanana_mcp_server.server"],
"cwd": "/absolute/path/to/nanobanana-2-polzaia-mcp-server",
"env": {
"POLZA_AI_API_KEY": "your-polza-api-key-here",
"POLZA_BASE_URL": "https://polza.ai/api",
"IMAGE_OUTPUT_DIR": "/absolute/path/to/output"
}
}
}
}
On macOS, add the same server to:
~/Library/Application Support/Claude/claude_desktop_config.json
Example:
{
"mcpServers": {
"nanobanana-polza": {
"command": "uvx",
"args": ["nanobanana-2-polzaia-mcp-server@latest"],
"env": {
"POLZA_AI_API_KEY": "your-polza-api-key-here",
"POLZA_BASE_URL": "https://polza.ai/api",
"IMAGE_OUTPUT_DIR": "/Users/demo/Documents/nanobanana"
}
}
}
}
To make installation as easy as the screenshot flow:
PyPIpyproject.toml and server.jsonserver.json to the MCP RegistryThe registry only stores metadata. The actual package still needs to exist on PyPI.
Before publishing:
ivanantigravity-lgtm/nanobanana-2-polzaia-mcp-serverPYTHONPYCACHEPREFIX=/tmp/pycache python3 -m compileall nanobanana_mcp_server tests
uv build
uv publish
server.json with mcp-publisherbrew install mcp-publisher
mcp-publisher login
mcp-publisher publish
This server uses:
POST /v1/mediaGET /v1/media/{id}POST /v1/storage/uploadGET /v1/storage/files/{id}DELETE /v1/storage/files/{id}through the Polza API.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.