Paretostudio MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 16 installs a week from npm. Last commit 24 Aug 2026.
Read, create, and install your ParetoStudio prompts, agents, and skills from any MCP client.
Today is the operative word: we check Paretostudio MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 paretostudio-mcp -e 'PARETOSTUDIO_API_KEY=<PARETOSTUDIO_API_KEY>' -- npx -y paretostudio-mcp
{
"mcpServers": {
"paretostudio-mcp": {
"command": "npx",
"args": [
"-y",
"paretostudio-mcp"
],
"env": {
"PARETOSTUDIO_API_KEY": "<PARETOSTUDIO_API_KEY>"
}
}
}
}
[mcp_servers.paretostudio-mcp]
command = "npx"
args = ["-y", "paretostudio-mcp"]
env = { PARETOSTUDIO_API_KEY = "<PARETOSTUDIO_API_KEY>" }
{
"mcpServers": {
"paretostudio-mcp": {
"command": "npx",
"args": [
"-y",
"paretostudio-mcp"
],
"env": {
"PARETOSTUDIO_API_KEY": "<PARETOSTUDIO_API_KEY>"
}
}
}
}
{
"servers": {
"paretostudio-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"paretostudio-mcp"
],
"env": {
"PARETOSTUDIO_API_KEY": "<PARETOSTUDIO_API_KEY>"
}
}
}
}
Put your own value in place of
<PARETOSTUDIO_API_KEY> (Your ParetoStudio API key (starts with psk_). Create one at https://paretostudio.io/settings under Developer).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
PARETOSTUDIO_API_URL (API base URL. Only change this when pointing at a self-hosted or staging instance).
Create your offers and launch AI Instagram DM sales agents from any MCP client, over OAuth.
Read, AI-create, and edit your Gisti checklists in plain language from any MCP client.
FL Studio MCP server: read, mix, compose, and edit your open FL Studio project from any MCP client.
Chat with your Zihin.ai agents, list them and load platform skills from any MCP client.
Sharebench — search & pull AI skills, agents, prompts & playbooks (SKILL.md) into any MCP client
Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client.
Train, test, install and review a website AI agent (CAAC Go) from any MCP client.
Create invoices and customers and record payments in BillingEngine from any MCP client.
Answers built from our own checks of this server.