mercury-spec-ops
Modular MCP server for programmatic prompt engineering. Provides intelligent prompt assembly for PRD generation, codebase analysis, and bug analysis with support for 31 technology stacks.
claude mcp add --transport stdio n0zer0d4y-mercury-spec-ops npx -y @n0zer0d4y/mercury-spec-ops
How to use
Mercury Spec Ops MCP Server exposes dynamic, AI-invocable tools for generating prompts and templates. It provides six programmable components: three prompts (PRD Prompt, Codebase Analysis Prompt, Bug Analysis Prompt) and three corresponding template resources (PRD Template, Codebase Analysis Template, Bug Analysis Template). These tools are designed to assemble technology-specific prompts and modular templates on demand, leveraging a large matrix of technologies, analysis dimensions, and template sections. You can invoke the server via MCP clients (such as Claude Desktop or Cursor) to generate targeted prompts and templates for Node.js/TypeScript, Python, and other tech stacks, with multi-value and comma-separated input support to analyze multiple technologies and focus areas simultaneously.
To use the server, configure it in your MCP client. The recommended approach is to run via npx, which fetches the latest version from npm. In Claude Desktop, point to an mcpServers entry using command npx and the package name, for example: npx -y @n0zer0d4y/mercury-spec-ops. In Cursor, you can similarly configure the JSON with command npx and the same package, optionally adding a timeout and stdio typing. If you install locally, you can run the server with node once you have built the project, and reference the local dist/server.js path in your MCP client configuration. The server’s modular design allows you to generate prompts and templates dynamically, selecting appropriate technology modules (e.g., node.js, TypeScript, React) and analysis dimensions (e.g., security, performance) as part of the prompt assembly and template building process.
How to install
Prerequisites:
- Node.js and npm/yarn installed on your machine
- Basic knowledge of MCP client configuration
Option A: Local Development
- Clone the repository and install dependencies:
git clone https://github.com/n0zer0d4y/mercury-spec-ops.git
cd mercury-spec-ops
npm install
npm run build
- Run the server locally:
npm run mcp
Option B: Install from npm (recommended for easy updates)
- Install globally via npm:
npm install -g @n0zer0d4y/mercury-spec-ops
- Run the server directly with npx (no installation required each run):
npx @n0zer0d4y/mercury-spec-ops
Option C: Use with MCP clients (configured in your client, see Usage section) to connect via stdio or network as needed.
Additional notes
Tips and common considerations:
- npx is recommended for getting the latest version of the server without additional installation steps.
- If running locally, remember to build before starting the server: npm run build.
- After configuration changes in your MCP client, restart the MCP client to apply changes.
- The npm package name to reference in MCP client configurations is @n0zer0d4y/mercury-spec-ops.
- Environment variables are optional; add any needed variables under the env key in your mcp_config if your deployment requires specific tokens, endpoints, or feature flags.
Related MCP Servers
context-engineering
Context Engineering is a MCP server that gives AI agents perfect understanding of your codebase. Eliminates context loss, reduces token usage, and generates comprehensive feature plans in minutes. Compatible with Cursor, Claude Code, and VS Code.
vulcan-file-ops
A Security-centric MCP Server providing enterprise-grade filesystem powers to AI assistants—read, write, edit, and manage files with comprehensive CVE protection and user-controlled access.. [Explore comprehensive code documentation and architecture details on DeepWiki](https://deepwiki.com/n0zer0d4y/vulcan-file-ops)
tavily
AI-powered search capabilities for AI assistants using the Tavily API and Model Context Protocol (MCP)
mcp-turso
MCP server for interacting with Turso-hosted LibSQL databases
athena-protocol
An AI tech lead in server form—this intelligent MCP agent validates your coding agent's strategy, analyzes impact, and catches critical issues before any code is written. Like having a senior engineer review every approach, ensuring thoughtful architecture and fewer regressions.
promptbook
Personal cookbook for AI prompts - MCP Server with RAG-powered semantic search