Verified

Prd MCP Server

Product Requirements Documents generated through AI-driven templates and validation.

Data last scanned 2 days ago · Reviewed 2 months ago

29★ 35TypeScriptMIT

Overview

This server streamlines the creation of structured Product Requirements Documents (PRDs) by connecting AI models to your workflow. Users can generate documents from descriptions and user stories, utilizing various providers including OpenAI, Anthropic, and local models. A fallback mechanism ensures that document generation persists even when AI services are unavailable. Beyond generation, the server includes a validator to ensure PRDs meet industry standards and specific rule sets. It provides access to a library of templates suitable for different product types, accessible via the standardized Model Context Protocol.

Our verdict

This tool carries a high-risk rating with a security score of 24/100. It is a community-maintained project that has not undergone editorial review, and with only one contributor, the lack of oversight increases the maintenance and bus-factor risk. Given these factors, it is best suited for experimental environments or non-critical documentation tasks, and should be avoided in sensitive production workflows.

Supports multiple AI providers including Gemini and Claude
Includes a validation tool for document completeness
Maintains a small supply-chain surface with seven dependencies
Features a template-based fallback system

Security-sensitive areas like authentication are not yet reviewed
Single maintainer increases long-term project risk
Last code commit occurred over four months ago

Setup

Claude Desktop

{
  "mcpServers": {
    "prd-mcp-server": {
      "args": [
        "-y",
        "prd-creator-mcp"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Compatibility

Client	Local	Docker	Remote	Read-only
Claude Desktop
Cursor
VS Code
Windsurf
ChatGPT

Frequently asked questions

›What are the system prerequisites for running this server?

You must have Node.js version 16 or higher and either npm or yarn installed on your machine.

›How can I configure my AI provider credentials?

You can copy the .env.example file to .env and set your API keys and preferred models, or use the update_provider_config MCP tool to update them at runtime.

›What happens if an AI provider is unavailable?

The server includes a fallback mechanism that automatically reverts to template-based generation when AI services are not accessible.

›Does the server support local AI models?

Yes, the server supports local models alongside OpenAI, Google Gemini, and Anthropic Claude, provided they are configured correctly.

›How can I view which AI providers are currently available?

You can use the list_ai_providers tool to see a list of all configured providers and their current availability status.