How to integrate Shortcut MCP with OpenAI Agents SDK

Framework Integration Gradient
Shortcut Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Shortcut to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Shortcut agent that can create a new epic for q3 goals, add a threaded comment to our launch epic, start a new iteration for next sprint, make a group for the mobile team through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Shortcut account through Composio's Shortcut MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Shortcut
  • Configure an AI agent that can use Shortcut as a tool
  • Run a live chat session where you can ask the agent to perform Shortcut operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Shortcut MCP server, and what's possible with it?

The Shortcut MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Shortcut account. It provides structured and secure access to your project management workspace, so your agent can perform actions like creating epics, organizing teams, adding comments, managing sprints, and labeling tasks on your behalf.

  • Epic and story management: Direct your agent to create new epics, add threaded comments, or reply to existing discussions to streamline project tracking and collaboration.
  • Iteration and sprint planning: Let your agent set up new iterations, define sprint cycles, and associate tasks or groups, making agile planning and progress tracking a breeze.
  • Team and group organization: Effortlessly create and customize new groups or teams, assign members, and link workflows to keep your workspace structure organized and aligned.
  • Label and category creation: Ask your agent to generate new categories or labels, helping you organize stories, tasks, and priorities for efficient project management.
  • Linked file integration: Enable your agent to attach or create linked files within Shortcut, keeping all your project resources and documentation accessible and up to date.

Supported Tools & Triggers

Tools
Create categoryCreate category allows you to create a new category in shortcut.
Create entity templateCreate a new entity template for the workspace.
Create epicCreate epic allows you to create a new epic in shortcut.
Create epic commentThis endpoint allows you to create a threaded comment on an epic.
Create epic comment commentThis endpoint allows you to create a nested comment reply to an existing epic comment.
Create groupCreates a new group in the shortcut system with customizable properties.
Create iterationThe createiteration endpoint allows you to create a new iteration in shortcut, which represents a time-boxed period for completing a set of stories or tasks.
Create labelCreate label allows you to create a new label in shortcut.
Create linked fileCreate linked file allows you to create a new linked file in shortcut.
Create milestone(deprecated: use 'create objective') create milestone allows you to create a new milestone in shortcut.
Create multiple storiesCreate multiple stories allows you to create multiple stories in a single request using the same syntax as [create story](https://developer.
Create objectiveCreate objective allows you to create a new objective in shortcut.
Create projectCreate project is used to create a new shortcut project.
Create storyCreate story is used to add a new story to your shortcut workspace.
Create story commentCreate comment allows you to create a comment on any story.
Create story from templateCreate story from template is used to add a new story derived from a template to your shortcut workspace.
Create story linkStory links (called story relationships in the ui) allow you create semantic relationships between two stories.
Create story reactionCreate a reaction to a story comment.
Create taskCreate task is used to create a new task in a story.
Delete categoryDelete category can be used to delete any category.
Delete custom fieldDeletes a specific custom field from the shortcut system using its unique public identifier.
Delete entity templateDeletes a specific entity template from the shortcut api.
Delete epicDelete epic can be used to delete the epic.
Delete epic commentThis endpoint allows you to delete a comment from an epic.
Delete fileDelete file deletes a previously uploaded file.
Delete iterationDeletes a specific iteration from the shortcut project management system.
Delete labelDelete label can be used to delete any label.
Delete linked fileDelete linked file can be used to delete any previously attached linked-file.
Delete milestone(deprecated: use 'delete objective') delete milestone can be used to delete any milestone.
Delete multiple storiesDelete multiple stories allows you to delete multiple archived stories at once.
Delete objectiveDelete objective can be used to delete any objective.
Delete projectDelete project can be used to delete a project.
Delete storyDelete story can be used to delete any story.
Delete story commentDelete a comment from any story.
Delete story linkRemoves the relationship between the stories for the given story link.
Delete story reactionDelete a reaction from any story comment.
Delete taskDelete task can be used to delete any previously created task on a story.
Disable iterationsDisables iterations for the current workspace
Disable story templatesDisables the story template feature for the workspace.
Enable iterationsEnables iterations for the current workspace
Enable story templatesEnables the story template feature for the workspace.
Get categoryGet category returns information about the selected category.
Get current member infoReturns information about the authenticated member.
Get custom fieldRetrieves detailed information about a specific custom field in shortcut using its unique public identifier.
Get entity templateGet entity template returns information about a given entity template.
Get epicGet epic returns information about the selected epic.
Get epic commentThis endpoint returns information about the selected epic comment.
Get epic workflowReturns the epic workflow for the workspace.
Get external link storiesGet stories which have a given external link associated with them.
Get fileGet file returns information about the selected uploadedfile.
Get groupRetrieves detailed information about a specific group in the shortcut workspace using its unique public identifier.
Get iterationRetrieves detailed information about a specific iteration in the shortcut project management system.
Get key resultGet key result returns information about a chosen key result.
Get labelGet label returns information about the selected label.
Get linked fileGet file returns information about the selected linked file.
Get memberReturns information about a member.
Get milestone(deprecated: use 'get objective') get milestone returns information about a chosen milestone.
Get objectiveGet objective returns information about a chosen objective.
Get projectGet project returns information about the selected project.
Get repositoryGet repository returns information about the selected repository.
Get storyGet story returns information about a chosen story.
Get story commentGet comment is used to get comment information.
Get story linkReturns the stories and their relationship for the given story link.
Get taskReturns information about a chosen task.
Get workflowGet workflow returns information about a chosen workflow.
List categoriesList categories returns a list of all categories and their attributes.
List category milestonesList category milestones returns a list of all milestones with the category.
List category objectivesReturns a list of all objectives with the category.
List custom fieldsRetrieves a list of all custom fields defined in the shortcut api.
List entity templatesList all the entity templates for the workspace.
List epic commentsGet a list of all comments on an epic.
List epicsList epics returns a list of all epics and their attributes.
List epic storiesGet a list of all stories in an epic.
List filesList files returns a list of all uploadedfiles in the workspace.
List groupsA group in our api maps to a "team" within the shortcut product.
List group storiesList the stories assigned to the group.
List iterationsRetrieves a list of all iterations in the shortcut project management system.
List iteration storiesGet a list of all stories in an iteration.
List label epicsList all of the epics with the label.
List labelsList labels returns a list of all labels and their attributes.
List label storiesList all of the stories with the label.
List linked filesList linked files returns a list of all linked-files and their attributes.
List membersReturns information about members of the workspace.
List milestone epics(deprecated: use 'list objective epics') list all of the epics within the milestone.
List milestones(deprecated: use 'list objectives') list milestones returns a list of all milestones and their attributes.
List objective epicsList all of the epics within the objective.
List objectivesList objectives returns a list of all objectives and their attributes.
List projectsList projects returns a list of all projects and their attributes.
List repositoriesList repositories returns a list of all repositories and their attributes.
List storiesList stories returns a list of all stories in a selected project and their attributes.
List story commentLists comments associated with a story
List workflowsReturns a list of all workflows in the workspace.
SearchSearch lets you search epics and stories based on desired parameters.
Search epicsSearch epics lets you search epics based on desired parameters.
Search iterationsSearch iterations lets you search iterations based on desired parameters.
Search milestonesSearch milestones lets you search milestones based on desired parameters.
Search objectivesSearch objectives lets you search objectives based on desired parameters.
Search storiesSearch stories lets you search stories based on desired parameters.
Search stories oldSearch stories lets you search stories based on desired parameters.
Story historyRetrieves the complete history of changes for a specific story in the shortcut project management system.
Unlink comment thread from slackUnlinks a comment from its linked slack thread (comment replies and slack replies will no longer be synced)
Unlink productboard from epicThis endpoint allows you to unlink a productboard epic.
Update categoryUpdate category allows you to replace a category name with another name.
Update custom fieldUpdate custom field can be used to update the definition of a custom field.
Update entity templateUpdate an entity template's name or its contents.
Update epicUpdate epic can be used to update numerous fields in the epic.
Update epic commentThis endpoint allows you to update a threaded comment on an epic.
Update fileUpdate file updates the properties of an uploadedfile (but not its content).
Update groupUpdates an existing group in the shortcut workspace.
Update iterationThis endpoint allows you to update an existing iteration in shortcut.
Update key resultUpdate key result allows updating a key result's name or initial, observed, or target values.
Update labelUpdate label allows you to replace a label name with another name.
Update linked fileUpdated linked file allows you to update properties of a previously attached linked-file.
Update milestone(deprecated: use 'update objective') update milestone can be used to update milestone properties.
Update multiple storiesUpdate multiple stories allows you to make changes to numerous stories at once.
Update objectiveUpdate objective can be used to update objective properties.
Update projectUpdate project can be used to change properties of a project.
Update storyUpdate story can be used to update story properties.
Update story commentUpdate comment replaces the text of the existing comment.
Update story linkUpdates the stories and/or the relationship for the given story link.
Update taskUpdate task can be used to update task properties.
Upload filesUpload files uploads one or many files and optionally associates them with a story.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Shortcut project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Shortcut.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Shortcut Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["shortcut"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only shortcut.
  • The router checks the user's Shortcut connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Shortcut.
  • This approach keeps things lightweight and lets the agent request Shortcut tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Shortcut. "
        "Help users perform Shortcut operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Shortcut and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Shortcut operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Shortcut.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Shortcut and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["shortcut"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Shortcut. "
        "Help users perform Shortcut operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Shortcut MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Shortcut.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Shortcut MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Shortcut MCP?

With a standalone Shortcut MCP server, the agents and LLMs can only access a fixed set of Shortcut tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Shortcut and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Shortcut tools.

Can I manage the permissions and scopes for Shortcut while using Tool Router?

Yes, absolutely. You can configure which Shortcut scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Shortcut data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.