Provides read-only access to Google Calendar events via public ICS feeds, enabling listing of events within date ranges and searching events by text query, with automatic handling of recurring events.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Calendar MCP Server list events from tomorrow to next Friday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides access to Google Calendar events via a public ICS feed.
List Events: Fetch events within a specific date range, handling recurring events automatically.
Search Events: Search for events by text (summary or description) within a 6-month window.
Caching: Implements a 5-minute memory cache to respect rate limits.
Related MCP server: ICS Calendar MCP Server
Python 3.11+
uv package manager (recommended)
Install dependencies using uv:
uv syncOpen main.py and set the ICS_URL constant to your public Google Calendar ICS URL:
ICS_URL = "https://calendar.google.com/calendar/ical/YOUR_CALENDAR_ID/public/basic.ics"Run the server using uv:
uv run main.pylist_eventsLists events between two dates.
Arguments:
start_date (string, ISO 8601, e.g., "2023-01-01")
end_date (string, ISO 8601, e.g., "2023-01-31")
Returns: A list of event objects with summary, start, end, description, and location.
search_eventsSearches for events matching a text query.
Arguments:
query (string)
Returns: A list of matching event objects found in the range of [30 days ago, 180 days future].
List calendar events within a specific date range, expanding recurring events.
Args:
start_date: Start of the range (ISO format, e.g., '2023-01-01')
end_date: End of the range (ISO format)
Returns:
List of events falling within the range.
| Name | Required | Description | Default |
|---|---|---|---|
| start_date | Yes | ||
| end_date | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly indicates this is a read operation (list) and specifies date range filtering and recurring event expansion. However, it doesn't mention pagination behavior, rate limits, authentication requirements, or error conditions that would be helpful for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly structured and concise - purpose statement first, followed by Args and Returns sections. Every sentence earns its place with no wasted words. The information is front-loaded with the core functionality stated immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (date range filtering with recurring event expansion) and the presence of an output schema, the description provides good coverage. It explains what the tool does, documents parameters, and mentions the return type. However, it could benefit from more behavioral context given the lack of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description compensates well by providing format examples (ISO format) and clarifying the purpose of both parameters. The Args section explicitly documents both required parameters with format guidance, adding significant value beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('List') and resource ('calendar events'), specifies the scope ('within a specific date range'), and distinguishes from sibling tool 'search_events' by mentioning the expansion of recurring events. This provides specific differentiation from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context about when to use this tool ('within a specific date range, expanding recurring events'), but doesn't explicitly state when NOT to use it or provide detailed alternatives. The existence of 'search_events' as a sibling tool is noted but not explained, leaving some ambiguity about tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for events matching a text query in summary or description.
Note: This searches a wide range (current year +/- 1 year) to be useful,
as text search on infinite recurrence is impossible without a range.
Args:
query: The text to search for.
Returns:
List of matching events.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively explains key behavioral traits: the temporal search range constraint ('current year +/- 1 year'), the rationale for this limitation ('text search on infinite recurrence is impossible without a range'), and the search scope ('summary or description'). This provides valuable operational context beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured with clear sections: purpose statement, important behavioral note, parameter explanation, and return value description. Every sentence adds value, with no redundant information. The formatting with 'Args:' and 'Returns:' sections enhances readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (search with temporal constraints), no annotations, and the presence of an output schema, the description provides good coverage. It explains the search behavior, temporal limitations, parameter meaning, and return format. The output schema handles return value details, so the description appropriately focuses on operational context rather than output structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate. It provides a clear explanation of the single parameter: 'query: The text to search for.' This adds essential semantic meaning that the schema lacks. The description also implies the parameter is required (matches the schema's required field).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search for events matching a text query in summary or description.' This specifies the verb (search), resource (events), and scope (summary/description fields). However, it doesn't explicitly differentiate from the sibling 'list_events' tool, which would be needed for a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context about when to use this tool: for text-based searches within event summaries/descriptions. The note about searching 'a wide range (current year +/- 1 year)' gives important temporal context. However, it doesn't explicitly contrast with the sibling 'list_events' tool or provide exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0list_eventssearch_eventsScored across 2 tools
The two tools have clearly distinct purposes: list_events retrieves events within a specific date range, while search_events finds events matching a text query across a broader timeframe. There is no overlap in functionality, and the descriptions make the distinction unambiguous.
Both tools follow a consistent verb_noun pattern (list_events and search_events), using snake_case and clear, descriptive verbs. The naming is predictable and aligned with common conventions for such operations.
With only two tools, this server feels severely under-scoped for a calendar domain. Essential operations like creating, updating, or deleting events are missing, making it incomplete for typical calendar management tasks. A calendar server should have at least basic CRUD operations to be functional.
The tool surface is significantly incomplete for a calendar server. While list_events and search_events provide read/search capabilities, there are no tools for creating, updating, or deleting events, which are core to calendar management. This leaves major gaps that will hinder agent workflows.
Calendar API for AI agents: events, availability, Google/Microsoft setup, scheduling, and iCal.
Extracts calendar events from natural-language text, with .ics and calendar links.
Google Events listings with dates, venues, and ticket links via a hosted MCP server.
Agent-Native Google Calendar - manage events, sync, and public booking