How do I install the server?
You can use npx (recommended) by adding a configuration snippet to `~/.aws/amazonq/mcp.json`, or clone the repository, install dependencies (`npm install`), build (`npm run build`), and reference the built `index.js`.
@cremich
基本情報
MCP Server implementation for promptz.dev
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"promptz.dev": {
"command": "npx",
"args": [
"-y",
"@promptz/mcp"
],
"env": {
"PROMPTZ_API_URL": "your-api-url-from-promptz.dev",
"PROMPTZ_API_KEY": "your-api-key-from-promptz.dev"
},
"disabled": false,
"autoApprove": []
}
}
}List available prompts from promptz.dev
Get a specific prompt by ID or name
List available project rules from promptz.dev
Get a specific project rule by name
A Model Context Protocol (MCP) server that exposes prompts and project rules from the promptz.dev API directly inside Amazon Q Developer, eliminating the need to copy-paste and reducing context switching.
Obtain API credentials from promptz.dev/mcp, then add the server configuration to your Amazon Q Developer MCP client settings file (~/.aws/amazonq/mcp.json) using either npx (recommended) or a local installation. Once connected, you can search and execute prompts or manage project rules via natural language in Amazon Q Developer.
~/.promptz/logs/mcp-server.log.You can use npx (recommended) by adding a configuration snippet to `~/.aws/amazonq/mcp.json`, or clone the repository, install dependencies (`npm install`), build (`npm run build`), and reference the built `index.js`.
Go to [promptz.dev/mcp](https://promptz.dev/mcp) and copy the MCP settings, including your API Key and API URL.
You can search and execute prompts, search for project rules, and (with compatible tools) add or update those rules in your workspace.
Check that your API credentials are correct, ensure the server configuration is valid, and look for error messages in the logs at `~/.promptz/logs/mcp-server.log`. You can also use the MCP Inspector for debugging.
Yes, the server only provides read access to prompts and project rules; it does not implement any write operations.
🚀 The fast, Pythonic way to build MCP servers and clients.
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
不止于 CSS
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
コメント