Claude Prompts MCP server for AI agents

Claude Prompts MCP Server is a production-ready Model Context Protocol (MCP) server that provides intelligent prompt orchestration and framework-driven AI workflows. It offers seamless integration with Claude Desktop, Cursor Windsurf, and any other MCP client through its universal compatibility.

Installation

Get the server running in under a minute with these commands:

# Clone, install, build, and start
git clone https://github.com/minipuft/claude-prompts-mcp.git
cd claude-prompts-mcp/server && npm install && npm run build && npm start

Client Integration

Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "claude-prompts-mcp": {
      "command": "node",
      "args": ["E:\\path\\to\\claude-prompts-mcp\\server\\dist\\index.js"],
      "env": {
        "MCP_PROMPTS_CONFIG_PATH": "E:\\path\\to\\claude-prompts-mcp\\server\\prompts\\promptsConfig.json"
      }
    }
  }
}

Cursor Windsurf & Other MCP Clients

Configure your MCP client with:

Command: node
Args: ["path/to/claude-prompts-mcp/server/dist/index.js"]
Environment (Optional): MCP_PROMPTS_CONFIG_PATH=path/to/prompts/promptsConfig.json

Claude Code CLI

For Claude Code CLI users:

claude mcp add-json claude-prompts-mcp '{"type":"stdio","command":"node","args":["path/to/claude-prompts-mcp/server/dist/index.js"],"env":{}}'

Usage

The server provides three main MCP tools that you can use within conversations:

Prompt Engine

Execute prompts with automatic type detection:

# Simple prompt execution
prompt_engine >>friendly_greeting name="Developer"

# Content analysis with framework enhancement
prompt_engine >>content_analysis input="research data"

# Run multi-step LLM-driven chains
prompt_engine >>code_review_optimization_chain target_code="..." language_framework="TypeScript"

Prompt Manager

Manage your prompt library:

# List available prompts
prompt_manager list filter="category:analysis"

# Create new prompts
prompt_manager create name="code_reviewer" type="template" \
  content="Analyze {{code}} for security, performance, and maintainability"

# Analyze prompt structure
prompt_manager analyze_type prompt_id="my_prompt"

System Control

Manage framework selection and system status:

# Switch thinking framework
system_control switch_framework framework="ReACT" reason="Problem-solving focus"

# View system analytics
system_control analytics include_history=true

# Check system status
system_control status

Execution Tiers

The server supports three execution tiers:

1. Simple Prompt Execution

Single-step prompt execution with variable substitution.

2. Template Processing

Framework-enhanced templates using the Nunjucks templating engine:

Analyze {{content}} for {% if focus_area %}{{focus_area}}{% else %}general{% endif %} insights.

{% for requirement in requirements %}
- Consider: {{requirement}}
{% endfor %}

3. Chain Workflows

Multi-step LLM-driven workflows with state management:

# Comprehensive Code Review

## User Message Template

**Target Code**: {{target_code}}
**Language/Framework**: {{language_framework}}

## Step 1: Structure & Organization Analysis
Analyze code architecture, organization, patterns, naming conventions...

**Output Required**: Structural assessment with identified patterns.

---

## Step 2: Functionality & Logic Review
Examine business logic correctness, edge cases, error handling...

**Output Required**: Logic validation with edge case analysis.

Thinking Frameworks

The server implements four structured thinking methodologies:

CAGEERF: Context, Analysis, Goals, Execution, Evaluation, Refinement, Framework
ReACT: Reasoning and Acting pattern for systematic problem-solving
5W1H: Who, What, When, Where, Why, How analysis
SCAMPER: Creative problem-solving (Substitute, Combine, Adapt, Modify, Put to other uses, Eliminate, Reverse)

Switch between frameworks with:

system_control switch_framework framework="ReACT" reason="Problem-solving focus"

Configuration

Server Configuration

Customize server behavior in config.json:

{
  "server": {
    "name": "Claude Custom Prompts MCP Server",
    "version": "1.0.0",
    "port": 9090
  },
  "prompts": {
    "file": "promptsConfig.json",
    "registrationMode": "name"
  },
  "transports": {
    "default": "stdio",
    "sse": { "enabled": false },
    "stdio": { "enabled": true }
  }
}

Prompt Organization

Structure your AI command library in promptsConfig.json:

{
  "categories": [
    {
      "id": "development",
      "name": "🔧 Development",
      "description": "Code review, debugging, and development workflows"
    },
    {
      "id": "analysis",
      "name": "📊 Analysis",
      "description": "Content analysis and research prompts"
    }
  ],
  "imports": [
    "prompts/development/prompts.json",
    "prompts/analysis/prompts.json"
  ]
}

Advanced Features

Hot-Reload System

The server automatically detects changes to prompt files and reloads them without requiring a restart. Simply edit your prompt files and the changes will be immediately available.

Template Engine

Use Nunjucks templating for dynamic prompts with:

Conditional logic ({% if condition %}...{% endif %})
Loops and iteration ({% for item in items %}...{% endfor %})
Filters and transformations ({{ variable | filter }})
Template inheritance and reuse

Chain Workflows

Build sophisticated AI workflows using either:

LLM-Driven Chains: Step-by-step instructions in markdown templates
Modular Prompt Chains: Orchestrate multiple prompts with explicit data flow

Real-Time Management

Manage prompts dynamically while the server runs:

# Update prompts with intelligent re-analysis
prompt_manager update id="analysis_prompt" content="new template"

# Hot-reload with comprehensive validation
system_control reload reason="updated templates"

Transport Support

The server supports multiple transports:

STDIO: For desktop clients (default)
Server-Sent Events (SSE): For web-based clients
HTTP Endpoints: For health checks and data queries

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "claude-prompts-mcp" '{"command":"node","args":["path/to/claude-prompts-mcp/server/dist/index.js"],"env":{"MCP_PROMPTS_CONFIG_PATH":"path/to/claude-prompts-mcp/server/promptsConfig.json"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "claude-prompts-mcp": {
            "command": "node",
            "args": [
                "path/to/claude-prompts-mcp/server/dist/index.js"
            ],
            "env": {
                "MCP_PROMPTS_CONFIG_PATH": "path/to/claude-prompts-mcp/server/promptsConfig.json"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "claude-prompts-mcp": {
            "command": "node",
            "args": [
                "path/to/claude-prompts-mcp/server/dist/index.js"
            ],
            "env": {
                "MCP_PROMPTS_CONFIG_PATH": "path/to/claude-prompts-mcp/server/promptsConfig.json"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect