Claude Prompts MCP Server is a powerful implementation of the Model Context Protocol (MCP) that allows you to manage and execute AI prompts through conversation. This server works with Claude Desktop, Cursor Windsurf, and any MCP-compatible client, enabling advanced prompt management with features like hot-reload, templating, and multi-step workflows.
Get started with a simple one-command installation:
git clone https://github.com/minipuft/claude-prompts-mcp.git
cd claude-prompts-mcp/server && npm install && npm run build && npm start
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\\promptsConfig.json"
}
}
}
}
Configure your MCP client with:
node["path/to/claude-prompts-mcp/server/dist/index.js"]MCP_PROMPTS_CONFIG_PATH=path/to/promptsConfig.jsonPro Tip: Always use absolute paths for reliable integration.
Once installed, you can interact with the server through your MCP client:
Discover available prompts:
>>listprompts
Execute a prompt:
>>friendly_greeting name="Developer"
Execute a prompt with JSON data:
>>research_prompt {"topic": "AI trends", "depth": "comprehensive", "format": "executive summary"}
You can create and modify prompts directly through conversation with your AI assistant:
"Create a prompt called 'bug_analyzer' that helps me debug code issues systematically"
Refine existing prompts:
"Make the bug_analyzer prompt also suggest performance improvements"
Fine-tune your server's 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 }
}
}
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"
]
}
Create dynamic prompts using Nunjucks templating:
Analyze {{content}} for {% if focus_area %}{{focus_area}}{% else %}general{% endif %} insights.
{% for requirement in requirements %}
- Consider: {{requirement}}
{% endfor %}
{% if previous_context %}
Build upon: {{previous_context}}
{% endif %}
Build sophisticated workflows that connect multiple prompts:
{
"id": "content_analysis_chain",
"name": "Content Analysis Chain",
"isChain": true,
"chainSteps": [
{
"stepName": "Extract Key Points",
"promptId": "extract_key_points",
"inputMapping": { "content": "original_content" },
"outputMapping": { "key_points": "extracted_points" }
},
{
"stepName": "Analyze Sentiment",
"promptId": "sentiment_analysis",
"inputMapping": { "text": "extracted_points" },
"outputMapping": { "sentiment": "analysis_result" }
}
]
}
Manage your prompts without server restarts:
>>update_prompt id="analysis_prompt" content="new template"
>>modify_prompt_section id="research" section="examples" content="new examples"
>>reload_prompts reason="updated templates"
This server implements the Model Context Protocol (MCP) standard and works with:
It supports multiple transport methods including STDIO (for desktop clients) and Server-Sent Events (SSE) for web-based integrations.
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.
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.
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"
}
}
}
}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.
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.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. 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