check_status
Check the status of a visual generation request. Returns progress information and file details when completed.
LABSCO SUMMARY
Diagram generation becomes one call, with the polling folded inside it.
generate_and_wait joins submission and polling together, so a paragraph of prose comes back as a finished visual without the client tracking request IDs. The separate submit-and-poll path stays available for a batch that would otherwise block for too long. list_styles reports the styles on offer but points at the Napkin styles documentation for the full list, so a style_id may still need looking up there.
What it is
A Napkin AI client that submits visual generation requests and collects the files they produce.
What you get
- Visual generation from content plus context, with control over format, orientation, width and height, colour mode, transparent background, style ID, language, how many visuals to make and how they are sorted.
- A choice of loop: submit and poll the status yourself, or make the single call that waits for completion.
- Delivery either as base64 data pulled from the file URL a status response carries, or written straight into storage configured on the server.
- A dry run, a style listing and an API key check, for confirming a setup before a real generation.
Requirements
NAPKIN_API_KEY, which verify_api_key exists to confirm. generate_and_save additionally needs storage configured in the server settings; without it, finished files come back through download_visual.
Setup effort
One command plus a key — npm install -g napkin-ai-mcp, then supply credentials
USE CASES
01
Getting a diagram out of a paragraph you already wrote
One call takes the text, the surrounding context and the format you want, and returns the finished visual.
02
Keeping the conversation moving while a batch renders
Fire the request, check back on it when convenient, and pull the file down once the status response names it.
03
Writing generated visuals straight into a project folder
Skips the base64 round trip by having the server put the finished file into the storage it was configured with.
04
Confirming the setup before spending a generation
Check the key first, then see which styles are on offer, so a style_id is not guessed at.
7 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
download_visual
Download a generated visual file as base64-encoded data. Use the URL from check_status response's generated_files array.
generate_and_save
Generate a visual, wait for completion, and save to configured storage. Requires storage to be configured in server settings.
generate_and_wait
Generate a visual and wait for completion. Combines generate_visual and polling check_status into a single operation.
generate_visual
Submit a visual generation request to Napkin AI. Returns a request ID for tracking. Use check_status to poll for completion.
list_styles
Get information about available visual styles. Note: For the full list, visit https://api.napkin.ai/docs/styles/index.html
verify_api_key
Verify that the configured Napkin AI API key is valid. Use this to test your setup before generating visuals.
BEFORE YOU INSTALL
What to know first
Tools you get
7 tools when we connected. generate_and_save fails with Storage not configured until you set NAPKIN_STORAGE_TYPE and that backend's credentials, so a bare install has six working tools.
Requires
- npx on PATH
- Node.js 18 or later
- NAPKIN_API_KEY in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 7 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g napkin-ai-mcpMCP Clients
Claude Desktop, Windsurf, Cline
JSON
{
"mcpServers": {
"napkin-ai": {
"command": "npx",
"args": [
"-y",
"napkin-ai-mcp"
],
"env": {
"NAPKIN_API_KEY": "<YOUR_NAPKIN_API_KEY>"
}
}
}
}Claude Desktop — local storage
CLAUDE DESKTOP — LOCAL STORAGE · JSON
{
"mcpServers": {
"napkin-ai": {
"command": "npx",
"args": [
"-y",
"napkin-ai-mcp"
],
"env": {
"NAPKIN_API_KEY": "<YOUR_NAPKIN_API_KEY>",
"NAPKIN_STORAGE_TYPE": "local",
"NAPKIN_STORAGE_LOCAL_DIR": "/Users/<YOUR_USERNAME>/napkin-visuals"
}
}
}
}/Users/<YOUR_USERNAME>/napkin-visuals is the absolute path of the folder where visuals should be saved, and <YOUR_NAPKIN_API_KEY> is your Napkin AI API key (in developer preview — request access from api@napkin.ai).
Claude Code, Cursor
JSON
{
"mcpServers": {
"napkin-ai": {
"command": "npx",
"args": [
"-y",
"napkin-ai-mcp"
],
"env": {
"NAPKIN_API_KEY": "<YOUR_NAPKIN_API_KEY>",
"NAPKIN_STORAGE_TYPE": "local",
"NAPKIN_STORAGE_LOCAL_DIR": "./visuals"
}
}
}
}Continue
CONTINUE · JSON
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"napkin-ai-mcp"
],
"env": {
"NAPKIN_API_KEY": "<YOUR_NAPKIN_API_KEY>"
}
}
}
]
}
}
