How do I configure this server with an MCP client?
Add an entry to the client's MCP settings JSON with the command `node` and args pointing to the built `dist/server.js`, or use `npx tsx` with the source file during development.
@tubone24
基本信息
This server allows you to create, organize, and serve prompt templates that can be used by MCP clients for various tasks like meeting analysis, content summarization, and blog post creation.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Prompt Templates Server is a Model Context Protocol (MCP) server that provides the "prompts" primitive for managing and serving customizable prompt templates. It allows users to create, organize, and serve prompt templates for tasks like meeting analysis, content summarization, and blog post creation.
Install with npm install, build with npm run build, and start with npm start. Configure an MCP client (e.g., Claude Desktop) by adding the server to its MCP settings JSON, pointing to the compiled dist/server.js or using tsx during development. Templates are loaded from the templates directory automatically.
templates directoryAdd an entry to the client's MCP settings JSON with the command `node` and args pointing to the built `dist/server.js`, or use `npx tsx` with the source file during development.
Node.js and npm are required. During development, TypeScript and tsx are needed for hot-reloading.
Create a subdirectory inside `templates/` with a descriptive name, containing a `config.yaml` file (for metadata and argument definitions) and a `template.md` file (for the prompt content with Mustache placeholders).
Placeholders use double curly braces, e.g., `{{ argument_name }}`. Argument names must match the `name` field in `config.yaml`.
Yes. In `config.yaml`, set `required: false` for an argument. The server will still substitute it if provided, but won't require it.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
不止于 CSS

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
评论