About Shortcut.com MCP Server
An MCP server for accessing and searching Shortcut.com tickets, intended for teams managing project work with AI assistants. Alongside story lookup, it supports creation, updates, comments, and retrieval of workflow states and projects.
Key features
- 01List and search stories
- 02Retrieve story details
- 03Create and update stories
- 04Add comments to stories
- 05Retrieve workflow states and projects
- 06Provide story resources and template prompts
Use cases
- 01Find project tickets matching criteria
- 02Review and edit ticket details
- 03Add comments to tickets
- 04Generate bug report or feature request templates
MCP support
The server provides MCP clients with Shortcut.com story resources, search and editing tools, and prompts for bug reports and feature requests.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEShortcut.com MCP Server
An implementation of a Model Context Protocol (MCP) server for accessing and searching tickets on Shortcut.com.
Overview
This project implements an MCP server that allows Claude and other MCP-compatible AI assistants to interact with Shortcut.com's ticket management system. With this integration, AI assistants can:
- List and search for stories (tickets) in Shortcut
- Get detailed information about specific stories
- Create new stories
- Update existing stories
- Add comments to stories
- Retrieve workflow states and projects
Prerequisites
- Python 3.10+
- Shortcut.com API token
Installation
-
Clone this repository:
git clone https://github.com/yourusername/mcp-server-shortcut.git cd mcp-server-shortcut -
Create a virtual environment and install dependencies:
# Using uv (recommended) curl -LsSf https://astral.sh/uv/install.sh | sh # For Mac/Linux uv venv source .venv/bin/activate # On Mac/Linux or .venv\Scripts\activate on Windows uv pip install -r requirements.txt # Using pip python -m venv venv source venv/bin/activate # On Mac/Linux or venv\Scripts\activate on Windows pip install -r requirements.txt -
Create a
.envfile in the project root directory with your Shortcut API token:SHORTCUT_API_TOKEN=your_token_here SERVER_PORT=5000 SERVER_HOST=0.0.0.0 DEBUG_MODE=True
Running the Server
Start the MCP server using:
python -m src.server
Configuring Claude Desktop
To use this MCP server with Claude Desktop:
-
Edit the Claude Desktop configuration file:
- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- Mac:
-
Add the MCP server configuration:
{ "mcpServers": { "shortcut": { "command": "python", "args": ["-m", "src.server"], "env": { "SHORTCUT_API_TOKEN": "your_token_here" } } } } -
Restart Claude Desktop.
Available MCP Capabilities
Resources
shortcut://stories- Access a list of storiesshortcut://story/{story_id}- Access a specific story
Tools
list_stories- List stories with optional filteringsearch_stories- Search for stories using text queriesget_story_details- Get detailed information about a specific storycreate_story- Create a new storyupdate_story- Update an existing storyadd_comment- Add a comment to a storylist_workflow_states- List all workflow stateslist_projects- List all projects
Prompts
create_bug_report- Generate a template for bug reportscreate_feature_request- Generate a template for feature requests
Project Structure
src/- Source code directoryserver.py- Main MCP server implementationconfig.py- Configuration managementshortcut_client.py- Client for the Shortcut APIutils.py- Utility functions and data models
requirements.txt- Project dependencies.env- Environment variables (not tracked in git)
Development
Adding New Capabilities
To add a new capability to the MCP server:
- Add any new API methods to
shortcut_client.py - Define Pydantic models in
utils.pyif needed - Implement the MCP functionality using decorators in
server.py:- Use
@mcp.resource()for read-only resources - Use
@mcp.tool()for actions that can modify data - Use
@mcp.prompt()for generating templates or structured text
- Use
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.