Shortcut MCP Server

What does “Shortcut” MCP Server do?

The Shortcut MCP (Model Context Protocol) Server acts as a bridge between AI assistants and the Shortcut project management platform, enabling seamless integration of Shortcut data and workflows into AI-driven development environments. By connecting AI agents with external data sources like Shortcut, the MCP server empowers users to automate project management tasks, retrieve and update stories, manage tickets, and interact with Shortcut’s API—all from within their preferred development tool. This enhances productivity by allowing AI assistants to perform complex Shortcut operations, such as querying project status or managing story details, directly through standardized MCP protocols. As a result, developers and teams can streamline their workflows, keep project context up-to-date, and unlock new automation possibilities, all without leaving their development environment.

List of Prompts

No information available.

List of Resources

No information available.

List of Tools

No information available.

Use Cases of this MCP Server

• Project management automation: Integrate Shortcut tasks and stories into AI-assisted workflows to automate routine management operations.
• Ticket and story retrieval: Allow AI agents to fetch and present Shortcut ticket data, enabling quick access to project status and updates.
• Story and ticket creation: Enable AIs to generate new Shortcut stories or tickets based on user commands or workflow triggers.
• AI-powered project insights: Leverage Shortcut data for reporting or summarization by AI, supporting better planning and retrospectives.
• Workflow orchestration: Use AI to trigger and manage Shortcut workflows, such as moving stories between states or assigning tasks programmatically.

How to set it up

Windsurf

1. Open the Windsurf MCP Configuration Panel.
2. Click Add custom server.
3. Add the following details and save the file:

   {
     "mcpServers": {
       "shortcut": {
         "command": "npx",
         "args": [
           "-y",
           "@shortcut/mcp@latest"
         ],
         "env": {
           "SHORTCUT_API_TOKEN": "<YOUR_SHORTCUT_API_TOKEN>"
         }
       }
     }
   }
   

4. Save and restart Windsurf if necessary.
5. Verify setup by confirming the server status in the configuration panel.

Cursor

1. Open or create the mcp.json file (located at ~/.cursor/mcp.json or <project-root>/.cursor/mcp.json).
2. Add the following details and save the file:

   {
     "mcpServers": {
       "shortcut": {
         "command": "npx",
         "args": [
           "-y",
           "@shortcut/mcp@latest"
         ],
         "env": {
           "SHORTCUT_API_TOKEN": "<YOUR_SHORTCUT_API_TOKEN>"
         }
       }
     }
   }
   

3. Save and restart Cursor if needed.
4. Verify the MCP server is recognized in Cursor settings.

Claude Code

1. Open the Claude Code configuration file at ~/.claude.json.
2. Find the projects > mcpServers section and add the following:

   {
     "projects": {
       "mcpServers": {
         "shortcut": {
           "command": "npx",
           "args": [
             "-y",
             "@shortcut/mcp@latest"
           ],
           "env": {
             "SHORTCUT_API_TOKEN": "<YOUR_SHORTCUT_API_TOKEN>"
           }
         }
       }
     }
   }
   

3. Save the file.
4. Restart Claude Code if necessary.
5. Verify setup through the Claude CLI or UI.

Cline

No specific instructions provided.

Securing API Keys

You should store sensitive keys such as SHORTCUT_API_TOKEN in the env object within your MCP server configuration.

Example:

{
  "mcpServers": {
    "shortcut": {
      "command": "npx",
      "args": [
        "-y",
        "@shortcut/mcp@latest"
      ],
      "env": {
        "SHORTCUT_API_TOKEN": "<YOUR_SHORTCUT_API_TOKEN>"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "shortcut": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “shortcut” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The Shortcut MCP server is well-documented in terms of setup and integration with major development platforms, but lacks public documentation about its specific tools, prompt templates, or resources exposed to AI clients. Its focus on project management automation is clear, but the absence of details on prompts, resources, and tools limits its immediate utility for advanced MCP workflows.

MCP Score

Overall rating: 4/10
The MCP server is easy to set up and has a clear use case, but the lack of information on prompts, resources, and tools reduces its overall utility and discoverability.