# AI-SDLC Prompts

> AI-SDLC Prompts is an open-source MCP server for ai models and llm tooling. Serve 112 bilingual SDLC prompts to coding agents, each with an autonomy contract. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI
- **Website:** https://prompts.lionsystems.com.mx
- **Repository:** https://github.com/dleon55/ai-sdlc-prompts/tree/HEAD/mcp-server
- **MCP Registry name:** io.github.dleon55/ai-sdlc-prompts
- **Categories:** AI models and LLM tooling, developer tools
- **Listing updated:** 2026-11-14

## About

Every prompt arrives with an operating contract that sets a ceiling on how far the agent may go, which tools it may use, when it must stop and ask, and what evidence its output has to include. The contract is appended by default when a prompt is resolved, so an agent that executes instead of merely drafting still sees its limits.

The library is organised in sections numbered 00 to 17 and covers repository scaffolding, governance files for AI agents, project charters and risk registers, codebase comprehension, design, implementation, testing, CI/CD and documentation. Each prompt exists in Spanish and English.

The server is read-only and runs locally over stdio from the npm package. It writes nothing to your repository, to GitHub or to any external system; all text is served from a prebuilt JSON file. Server code is MIT and the prompts are CC BY 4.0.

## Features

- **Operating contract per prompt:** Each prompt carries an autonomy ceiling, allowed tools, stop conditions and minimum evidence.
- **Spanish and English:** Every one of the 112 prompts is available in both languages.
- **Filtered listing:** Browse by section, risk level, autonomy level or free text.
- **Placeholder resolution:** Fill in prompt variables and see which required ones are still missing.
- **Framework preamble:** Fetch the mandatory framework block that precedes every prompt.
- **Read-only by design:** Nothing is written to repositories or external services.

## Good for

- Give Claude Code a governed prompt for scaffolding a new repository
- Pull an incident-response or threat-modelling prompt into Cursor without copy and paste
- Set up governance files so several agents follow the same rules
- Draft a project charter or risk register with an agent
- Keep agent autonomy limited on risky changes

## Install

### Claude Code (Terminal)

```sh
claude mcp add ai-sdlc-prompts -- npx -y ai-sdlc-prompts-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "ai-sdlc-prompts": {
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "ai-sdlc-prompts": {
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "ai-sdlc-prompts": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "ai-sdlc-prompts": {
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "ai-sdlc-prompts": {
      "command": "npx",
      "args": [
        "-y",
        "ai-sdlc-prompts-mcp"
      ]
    }
  }
}
```

## Tools

- `list_prompts`: Lists prompts, optionally filtered by section, risk, autonomy level or free text.
- `get_prompt`: Returns the full detail of one prompt by id, including its contract and recommended next prompts.
- `resolve_prompt`: Substitutes placeholders and appends the operating contract.
- `get_framework`: Returns the mandatory framework preamble.

## FAQ

### What does the operating contract contain?

An autonomy ceiling, the tools the agent may use, the conditions where it must stop and ask, and the minimum evidence its output must include.

### Can the contract be turned off?

Yes, passing append_contract as false returns the raw prompt text, which is meant for inspection rather than normal use.

### How is it installed?

Run it with npx ai-sdlc-prompts-mcp, or add it to your client's MCP configuration with the npx command.

### What are the licences?

The server code is MIT and the prompts it serves are CC BY 4.0, so commercial use is allowed with attribution.

### Is AI-SDLC Prompts free?

Yes. AI-SDLC Prompts is open source, so you can use and self-host it for free.

### How do I add AI-SDLC Prompts to Claude Code?

Run this command in your terminal: claude mcp add ai-sdlc-prompts -- npx -y ai-sdlc-prompts-mcp

### What are the best alternatives to AI-SDLC Prompts?

The closest alternatives to AI-SDLC Prompts are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/ai-sdlc-prompts
