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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。