supershift-mcp
Enables AI clients to read and analyze Supershift schedules from exported calendar data, providing tools to list, filter, summarize shifts, detect conflicts, and estimate pay.
README
supershift-mcp
supershift-mcp is a small MCP and HTTP bridge for schedules exported from
Supershift.
Research result
As of 2026-06-21, I could not find a documented public Supershift API or an existing Supershift MCP server. The public Supershift pages document local use, optional Cloud Sync, calendar sharing, and export to external calendars. Google Play also lists Android Calendar Export as a Pro feature.
This project therefore uses the stable integration point Supershift exposes to
users: exported calendar data, usually an .ics file or a private calendar URL
from the target calendar provider.
It deliberately does not reverse engineer Supershift Cloud Sync or private app storage. The current bridge is read-oriented. It can list shifts, find the next shift, and summarize hours from an exported calendar.
Features
- MCP stdio server for AI clients
- Optional FastAPI HTTP API
- Reads local
.icsfiles or HTTPS calendar URLs - Lists shifts in a date range
- Returns the next shift
- Summarizes worked hours by shift title
Install
python3 -m pip install "git+https://github.com/Zyrial96/supershift-mcp.git"
For local development:
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e ".[api,dev]"
pytest
Configure
Set SUPERSHIFT_ICS to either a local .ics file or a private calendar URL:
export SUPERSHIFT_ICS="/path/to/supershift.ics"
or:
export SUPERSHIFT_ICS="https://calendar.example/private/supershift.ics"
On Android, Supershift Pro can export shifts to Google Calendar. You can then
use a private iCal URL for that calendar, or periodically export an .ics file.
Run MCP
supershift-mcp
Example MCP client configuration:
{
"mcpServers": {
"supershift": {
"command": "supershift-mcp",
"env": {
"SUPERSHIFT_ICS": "/path/to/supershift.ics"
}
}
}
}
Available tools:
calendar_status(calendar: str | None = None)list_shifts(start: str, end: str, calendar: str | None = None)filter_shifts(start: str, end: str, calendar: str | None = None, title_contains: str | None = None, location_contains: str | None = None, notes_contains: str | None = None, min_hours: float | None = None, max_hours: float | None = None)get_shift(uid: str, calendar: str | None = None)current_shift(at: str | None = None, calendar: str | None = None)shifts_on_date(day: str, calendar: str | None = None)next_shift(after: str | None = None, days: int = 90, calendar: str | None = None)summarize_shifts(start: str, end: str, calendar: str | None = None)summarize_by_period(start: str, end: str, period: str = "day", calendar: str | None = None, include_all_day: bool = False)detect_conflicts(start: str, end: str, calendar: str | None = None)rest_periods(start: str, end: str, calendar: str | None = None, minimum_hours: float = 11)free_days(start: str, end: str, calendar: str | None = None)export_shifts(start: str, end: str, output_format: str = "json", calendar: str | None = None)estimate_pay(start: str, end: str, hourly_rate: float, calendar: str | None = None, title_rates: dict[str, float] | None = None, currency: str = "EUR", include_all_day: bool = False)shift_titles(calendar: str | None = None)shift_locations(calendar: str | None = None)upcoming_shifts(days: int = 14, calendar: str | None = None)
Run HTTP API
Install the API extra first:
python -m pip install -e ".[api]"
Then start the server:
supershift-api
Endpoints:
GET /healthGET /shifts?start=2026-06-01&end=2026-07-01GET /shifts/filter?start=2026-06-01&end=2026-07-01&title_contains=NightGET /shifts/currentGET /shifts/next?days=30GET /shifts/date/2026-06-21GET /shifts/{uid}GET /summary?start=2026-06-01&end=2026-07-01GET /summary/period?start=2026-06-01&end=2026-07-01&period=weekGET /conflicts?start=2026-06-01&end=2026-07-01GET /rest-periods?start=2026-06-01&end=2026-07-01GET /free-days?start=2026-06-01&end=2026-07-01GET /export?start=2026-06-01&end=2026-07-01&output_format=csvGET /pay?start=2026-06-01&end=2026-07-01&hourly_rate=20GET /titlesGET /locations
Boundaries
This is not an official Supershift product. It cannot create or edit entries inside the Supershift Android app unless Supershift publishes a supported write API in the future. Writing directly into Cloud Sync or private app storage would be fragile and may violate user expectations or terms.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.