claude mcp add mcp-prompt-engine -- npx -y mcp-prompt-engine
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
Star count
18 โ ยท vasayxtx/mcp-prompt-engine ยท read from the repository page ยท (checked 2026-10-16 20:00:20)
Source
collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
Harvest history
first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร ยท listed by 10 sources
Score
score 1,003 ยท 18 โ ยท 10 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆๅก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository vasayxtx/mcp-prompt-engine๏ผfirst catalogued 2026-10-09๏ผlast seen 2026-10-16ใThere is no official certification or quality rating here โ we record sources and dates only.
A Model Control Protocol (MCP) server for managing and serving dynamic prompt templates using elegant and powerful text template engine. Create reusable, logic-driven prompts with variables, partials, and conditionals that can be served to any compatible MCP client like Claude Code, Claude Desktop, Gemini CLI, VSCode with Copilot, etc. Key Features - **MCP Compatible**: Works out-of-the-box with any MCP client that supports prompts. - **Powerful Go Templates**: Utilizes the full power of Go text/template syntax, including variables, conditionals, loops, and more. - **Reusable Partials**: Define common components in partial templates (e.g., _header.tmpl) and reuse them across your prompts. - **Prompt Arguments**: All template variables are automatically exposed as MCP prompt arguments, allowing dynamic input from clients. - **Hot-Reload**: Automatically detects changes to your prompt files and reloads them without restarting the server. - **Rich CLI**: A modern command-line interface to list, validate, and render templates for easy development and testing. - **Smart Argument Handling**: - Automatically parses JSON arguments (booleans, numbers, arrays, objects). - Injects environment variables as fallbacks for template arguments. - **Containerized**: Full Docker support for easy deployment and integration. Hosted deployment A hosted deployment is available on Fronteir AI. Getting Started 1. Installation Install using Go: (For other methods like Docker or pre-built binaries, see the Installation section below.) 2. Create a Prompt Create a prompts directory and add a template file. Let's create a prompt to help write a Git commit message. First, create a reusable partial named prompts/_git_commit_role.tmpl: : A brief, imperative-tense summary of changes [Optional longer description, explaining the "why" of the change. Use dash points for clarity.] Now, create a main prompt prompts/git_stage_commit.tmpl that uses this partial: 3. Validate Your Prompt Validate your prompt to ensure it has no syntax errors: 4. Connect MCP Server to Your Client Add MCP Server to your MCP client. See Connecting to Clients for configuration examples. 5. Use Your Prompt Your git_stage_commit prompt will now be available in your client! For example, in Claude Desktop, you can select the git_stage_commit prompt, provide the type MCP Prompt argument and get a generated prompt that will help you to do a commit with a perfect message. In Claude Code or Gemini CLI, you can start typing /git_stage_commit and it will suggest the prompt with the provided arguments that will be executed after you select it. --- Installation Pre-built Binaries Download the latest release for your OS from the GitHub Releases page. Build from Source Docker A pre-built Docker image is available. Mount your local prompts and logs directories to the container. You can also build the image locally with make docker-build. --- Usage Creating Prompt Templates Create a directory to store your prompt templates. Each template should be a .tmpl file using Go's text/template syntax with the following format: The first line comment ({{/* description */}}) is used as the prompt description, and the rest of the file is the prompt template.