NanoBanana Pro 2
mcpopen · packageio.github.u2n4/nanobanana-imagen-mcp · v1.1.2
4K AI image generation via NanoBanana Pro 2: Pro + Flash models, Google Search grounding
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
# once, as root:
# as_mcp DIR COMMAND...: runs COMMAND as the mcp user in DIR, its home, sandboxed as the
# units are: a package's install scripts can write to DIR only, as the server later can
as_mcp() {
local dir="$1"; shift
systemd-run --quiet --wait --pipe --collect --uid=mcp --gid=mcp \
-p WorkingDirectory="$dir" -p Environment=HOME="$dir" -p ReadWritePaths="$dir" \
-p NoNewPrivileges=true -p ProtectSystem=strict -p ProtectHome=true -p PrivateTmp=true \
-- "$@" </dev/null
}
install -d -m 0750 -o mcp -g mcp /var/lib/mcp/nanobanana-imagen
# nanobanana-imagen: its packages, installed whole before its unit starts (no session installs)
systemctl stop mcp-my-agent-nanobanana-imagen.service 2>/dev/null || true
as_mcp /var/lib/mcp/nanobanana-imagen uv tool install nanobanana-imagen-mcp==1.1.2
as_mcp /var/lib/mcp/nanobanana-imagen uv tool install mcp-proxy
#!/usr/bin/env bash
# nanobanana-imagen (io.github.u2n4/nanobanana-imagen-mcp), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-nanobanana-imagen.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec uvx mcp-proxy --host 127.0.0.1 --port 8101 --pass-environment -- uvx nanobanana-imagen-mcp==1.1.2
[Unit]
Description=MCP server nanobanana-imagen (toolset my-agent), generated by Hub
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=mcp
Group=mcp
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/nanobanana-imagen
WorkingDirectory=/var/lib/mcp/nanobanana-imagen
ExecStart=/opt/mcp/my-agent/bin/nanobanana-imagen.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/nanobanana-imagen
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
docker run --rm -p 127.0.0.1:8101:8000 ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx nanobanana-imagen-mcp==1.1.2'
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T23:05:59+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
# cp .env.example .env # fill the ${VAR}s
# docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
nanobanana-imagen:
image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
command:
- sh
- -c
- uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx nanobanana-imagen-mcp==1.1.2
ports:
- 127.0.0.1:8101:8000
volumes:
- uv-cache:/root/.cache/uv
healthcheck:
test:
- CMD
- python3
- -c
- import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/status')
interval: 30s
timeout: 5s
retries: 5
start_period: 2m
restart: unless-stopped
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T23:05:59+00:00).
# kubectl create namespace mcp
# kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
# kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: nanobanana-imagen
namespace: mcp
labels: &id001
app: nanobanana-imagen
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: nanobanana-imagen
image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
ports:
- containerPort: 8000
name: http
env: []
args:
- sh
- -c
- uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx nanobanana-imagen-mcp==1.1.2
readinessProbe:
httpGet:
path: /status
port: http
initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
name: nanobanana-imagen
namespace: mcp
spec:
selector:
app: nanobanana-imagen
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T23:05:59+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
nanobanana-imagen:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: nanobanana-imagen
image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
ports:
- containerPort: 8000
name: http
env: []
args:
- sh
- -c
- uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx nanobanana-imagen-mcp==1.1.2
readinessProbe:
httpGet:
path: /status
port: http
initialDelaySeconds: 10
# helm install my-agent helm/my-agent -n mcp
in the cloud
one click: the provider's deploy form opens filled in, in your own account- koyeb
-
Clients connect to the service's https://…koyeb.app address plus /mcp.
- azure
-
A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The deployment's outputs list the endpoints.
connect to it
copy what your client needsuvx nanobanana-imagen-mcp==1.1.2
{
"mcpServers": {
"nanobanana-imagen": {
"command": "uvx",
"args": [
"nanobanana-imagen-mcp==1.1.2"
]
}
}
}
#!/usr/bin/env bash # Registers every server with Claude Code (run once; `claude mcp list` to check). set -euo pipefail set -a; [ -f .env ] && source .env; set +a claude mcp add nanobanana-imagen -- uvx nanobanana-imagen-mcp==1.1.2
{
"mcpServers": {
"nanobanana-imagen": {
"command": "uvx",
"args": [
"nanobanana-imagen-mcp==1.1.2"
]
}
}
}
{
"servers": {
"nanobanana-imagen": {
"type": "stdio",
"command": "uvx",
"args": [
"nanobanana-imagen-mcp==1.1.2"
]
}
}
}
name: my-agent target: local servers: - hub: io.github.u2n4/nanobanana-imagen-mcp
- not probed yet: tools unpinned, ingest lists them
tools
Probe result: needs authbaremetal: MCPError: Connection closed; server stderr: ….cache/uv/archive-v0/AL0RySx-Bno6SSPWe-NFc/lib/python3.12/site-packages/nanobanana_mcp_server/server.py", line 79, in create_wrapper_app server_config = ServerConfig.from_env() ^^^^^^^^^^^^^^^^^^^^^^^ File "<path>", line 90, in from_env raise ValueError(AUTH_ERROR_MESSAGES["no_auth_configured"]) ValueError: No valid authentication configuration found. API Key: Set GEMINI_API_KEY or GOOGLE_API_KEY Vertex AI: Set GCP_PROJECT_ID (and optional…
runs · 1
the latest tests of this entry by the hub and its workers, newest first| date | worker | method | status | sandbox | reason |
|---|---|---|---|---|---|
| 2026-10-18 08:46 | local-mac-vm | baremetal | needs auth | gvisorghcr.io/astral-sh/uv:python3.12-bookworm-slim | baremetal: MCPError: Connection closed; server stderr: ….cache/uv/archive-v0/AL0RySx-Bno6SSPWe-NFc/lib/python3.12/site-packages/nanobanana_mcp_server/server.py"… |