Napkin runs on your own machine — the client starts it, so there is no endpoint to ping. 73 installs a week from npm. Last commit 2 Nov 2026.
Napkin AI visual generation MCP server for Model Context Protocol hosts
What the code does
We read the source, 23 h ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(outFd, pdfBuffer);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
A tool parameter here reaches a dangerous call
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server-napkin -e 'NAPKIN_API_KEY=<NAPKIN_API_KEY>' -- npx -y @mindstone/mcp-server-napkin{
"mcpServers": {
"mcp-server-napkin": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-napkin"
],
"env": {
"NAPKIN_API_KEY": "<NAPKIN_API_KEY>"
}
}
}
}[mcp_servers.mcp-server-napkin]
command = "npx"
args = ["-y", "@mindstone/mcp-server-napkin"]
env = { NAPKIN_API_KEY = "<NAPKIN_API_KEY>" }{
"mcpServers": {
"mcp-server-napkin": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-napkin"
],
"env": {
"NAPKIN_API_KEY": "<NAPKIN_API_KEY>"
}
}
}
}{
"servers": {
"mcp-server-napkin": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-napkin"
],
"env": {
"NAPKIN_API_KEY": "<NAPKIN_API_KEY>"
}
}
}
}Put your own value in place of
<NAPKIN_API_KEY> (Napkin AI API key).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
MCP_WORKSPACE_PATH (Workspace directory for saving generated visuals), NAPKIN_REQUEST_TIMEOUT_MS (Outbound HTTP request timeout in milliseconds (max 1800000)).
Alternatives to Napkin
same job, measured the same wayKling AI video generation MCP server for Model Context Protocol hosts
Gamma AI presentation generation MCP server for Model Context Protocol hosts
OpenAI image generation MCP server for Model Context Protocol hosts
Zendesk MCP server for Model Context Protocol hosts
GitLab MCP (Model Context Protocol) server for AI agents
ServiceNow ITSM MCP server for Model Context Protocol hosts
PandaDoc document automation MCP server for Model Context Protocol hosts
Fathom AI meeting transcription MCP server for Model Context Protocol hosts
Napkin — questions
Answers built from our own checks of this server.