paretostudio-mcp
Enables reading, searching, installing, and managing ParetoStudio prompts, agents, and skills from Claude Code, Cursor, or any MCP client, and can install agents/skills as files into Claude Code or Codex projects.
README
paretostudio-mcp
Read your ParetoStudio prompt, agent, and skill library from Claude Code, Cursor, and any MCP client. Install agents and skills as files into Claude Code.
Quick Start
1. Get your API key
Go to paretostudio.io/settings and navigate to Developer, then create an API Key.
2. Configure your client
Claude Code (.mcp.json in your project root):
{
"mcpServers": {
"paretostudio": {
"command": "npx",
"args": ["-y", "paretostudio-mcp@latest"],
"env": {
"PARETOSTUDIO_API_KEY": "psk_your_key_here"
}
}
}
}
Cursor (Settings > MCP):
{
"mcpServers": {
"paretostudio": {
"command": "npx",
"args": ["-y", "paretostudio-mcp@latest"],
"env": {
"PARETOSTUDIO_API_KEY": "psk_your_key_here"
}
}
}
}
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"paretostudio": {
"command": "npx",
"args": ["-y", "paretostudio-mcp@latest"],
"env": {
"PARETOSTUDIO_API_KEY": "psk_your_key_here"
}
}
}
}
Codex (~/.codex/config.toml):
[mcp_servers.paretostudio]
command = "npx"
args = ["-y", "paretostudio-mcp@latest"]
[mcp_servers.paretostudio.env]
PARETOSTUDIO_API_KEY = "psk_your_key_here"
3. Use it
Ask Codex, Claude, or your MCP client to "list my prompts" or "install my agent" — the tools are available automatically.
Available Tools
| Tool | Description |
|---|---|
list_prompts |
List all prompts in your library |
get_prompt |
Get full prompt content (all 6 steps) |
search_prompts |
Search prompts by title or description |
list_agents |
List all agents |
get_agent |
Get agent with full configuration |
search_agents |
Search agents |
list_skills |
List all skills |
get_skill |
Get skill with full configuration |
search_skills |
Search skills |
install_skill |
Install skill for Claude or Codex project layouts |
install_agent |
Download agent to .claude/agents/ |
install_bundle |
Install agent + skills in one operation |
create_prompt |
Create a new prompt |
update_prompt |
Update a prompt |
delete_prompt |
Delete a prompt |
create_skill |
Create a new skill |
update_skill |
Update a skill |
delete_skill |
Delete a skill |
create_agent |
Create a new agent |
update_agent |
Update an agent |
delete_agent |
Delete an agent |
Install tools never overwrite existing files by default. Pass overwrite: true
only when you intentionally want to replace an installed agent or skill.
For Codex project skills, call install_skill with client: "codex"; the skill
is written to .agents/skills/<name>/SKILL.md instead of .claude/skills/.
Write tools respect your plan's library caps (Free: 5 prompts / 2 agents / 2 skills; Pro and Team: unlimited).
Rate Limits
| Plan | Daily Requests | Write Access |
|---|---|---|
| Free | 50 | Yes — within plan caps (5 prompts / 2 agents / 2 skills) |
| Pro | 500 | Yes — unlimited |
| Team | 500 | Yes — unlimited, shared team library |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
PARETOSTUDIO_API_KEY |
Yes | -- | Your API key (starts with psk_) |
PARETOSTUDIO_API_URL |
No | https://paretostudio.io |
API base URL |
Source
The server source lives in the ParetoStudio application repository, because it
imports the same business rules the API enforces (src/rules/) — duplicating them
here would let the two drift apart. This repository is the public home of the
published package: the manifest registries read, the configuration examples, and
the documentation.
Releases are automatic: a version bump reaching main publishes to npm, and a CI
gate refuses a build whose server changed since the last bump.
Links
Privacy Policy
The server is a local process on your machine. It talks only to the
ParetoStudio API (https://paretostudio.io, or the PARETOSTUDIO_API_URL you
configure) using the API key you provide, and sends nothing anywhere else.
Privacy policy: paretostudio.io/privacy
Security
See SECURITY.md. Report vulnerabilities to support@paretostudio.io — not in public issues.
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.