# claude-prompts-mcp

Adds reusable prompt templates, multi-step chains with shared context, and validation gates to your AI coding agent.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 189
- Author: minipuft
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/minipuft/claude-prompts-mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/claude-prompts-mcp

## What it does

This MCP server sets up a structured prompt execution layer beside your agent. Instead of running isolated prompts, you trigger chained sequences that pass intermediate outputs down the line. Quality gates inspect results using either shell execution or model self-evaluations before moving forward.

Prompts live in YAML files with version history and rollback support. The `skills:export` tool converts these assets directly into native client skills. You can scaffold a workspace with `--init` or point the `MCP_RESOURCES_PATH` environment variable to a directory containing `config.jsonc`.

Codex hooks are experimental, require Codex CLI 0.117 or newer, and do not function on Windows systems. In clients like Cursor or Zed, the integration operates as a standard stdio MCP server without chain-tracking hooks.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add claude-prompts-mcp -- npx -y claude-prompts
```

### Codex

**Platform CLI**
```bash
codex mcp add claude-prompts-mcp -- npx -y claude-prompts
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "claude-prompts-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "claude-prompts"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "claude-prompts-mcp": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "claude-prompts"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add claude-prompts-mcp npx -y claude-prompts
```

## When to use it
- pass context across multi-step prompt chains
- verify intermediate agent output with shell commands
- manage versioned prompt templates in YAML files
- export workflows into native skills for different coding agents

## Example prompts
- Run a library evaluation chain: `>>tech_evaluation_chain library:'zod' context:'API validation'`
- Trigger research across steps: `>>research_chain topic:'remote team policies'`
- Export prompt chains into client skills using `skills:export`

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md