Which integrations are available for this server?

Allows interaction with Google Calendar API, enabling users to list, create, delete, and update calendar events.

How do I use Google Calendar MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Google Calendar MCP Server Show me my events for today" 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.

Google Calendar MCP Server

by rsc1102

Overview Schema Related Servers Score Discussions

Python

Local

Google Calendar MCP Server

This repository provides a Model Context Protocol (MCP) server that integrates with the Google Calendar API. It allows users to list, create, delete, and update calendar events. The server is designed to work with Anthropic's Claude Desktop as an MCP client.

🚀 Features

Interact with Google Calendar: list, add, delete, and update events
Seamless integration with Claude Desktop via MCP

Related MCP server: Google Calendar MCP Server

🧰 Prerequisites

A Google Account
Anthropic Claude Desktop

📦 Installation

Install UV Package Manager: Follow the instructions on the official UV installation guide.

Clone the Repository and Set Up Environment:

git clone https://github.com/rsc1102/Google_Calendar_MCP.git
cd Google_Calendar_MCP
uv sync

Create Google Cloud Credentials:
- Visit Google Cloud Console.
- Create a new project or select an existing one.
- Enable the Google Calendar API.
- Navigate to APIs & Services > Credentials.
- Click Create Credentials > OAuth Client ID:
  - Choose Desktop app as the application type.
  - Download the generated credentials.json file.
  - Place credentials.json inside the Google_Calendar_MCP directory.

🔌 Integration with Claude Desktop

Locate Configuration File: Open the claude_desktop_config.json file on your system:

Linux/macOS:

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

Windows (PowerShell):

code $env:AppData\Claude\claude_desktop_config.json

Add MCP Server Configuration: Add the following to the mcpServers section:

{
    "mcpServers": {
        "calendar": {
            "command": "uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/Google_Calendar_MCP",
                "run",
                "calendar_mcp.py"
            ]
        }
    }
}

Restart Claude Desktop.
Create a New Project in Claude Desktop.
Set Timezone: In the project's knowledge section, define your local timezone using the IANA Time Zone format (e.g., timeZone="America/New_York").
Start Chatting: Begin interacting with Claude to manage your Google Calendar events.
Note: When using the server for the first time, Google will prompt you to authenticate and grant permission to access your calendar.

🎬 In Action

https://github.com/user-attachments/assets/75da4943-15c4-4ec2-bc5d-af4af3509031

📬 Support

For issues or questions, please open an issue in this repository.

Available Tools

4 tools

create_eventA

Creates a calendar event using the provided details.

Args: start (str): Event start time in ISO 8601 format (e.g., '2025-04-06T10:00:00-07:00'). end (str): Event end time in ISO 8601 format (e.g., '2025-04-06T11:00:00-07:00'). timeZone (str): User timezone formatted as an IANA Time Zone Database name (e.g. "Europe/Zurich"). summary (str): Short title or subject of the event. description (str, optional): Detailed description or notes for the event. Defaults to None. location (str, optional): Physical or virtual location of the event. Defaults to None.

ParametersJSON Schema

Name	Required	Description	Default
`end`	Yes
`start`	Yes
`summary`	Yes
`location`	No
`timeZone`	Yes
`description`	No

TDQS

A3.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states it creates an event but does not mention required permissions, side effects (e.g., sending invitations), success/failure responses, or any mutation-related caveats. The lack of such context is a notable gap for a create operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact: a one-sentence purpose followed by a structured Args list. It is front-loaded with the action and then efficiently details each parameter without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the action and parameter semantics well, but lacks any mention of return value or error handling, and the tool has no output schema. Given there are six parameters and no annotations, the gap is minor; the essential invocation details are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description thoroughly compensates by documenting every parameter: ISO 8601 format with examples for start/end, IANA timezone for timeZone, and defaults for optional description/location. This adds significant meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Creates a calendar event using the provided details,' which clearly identifies the action (create) and the target resource (calendar event). This distinguishes it from sibling tools like list_events, update_event, and delete_event.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The tool's usage is implied by its name and the verb 'creates,' but there is no explicit guidance on when to choose this over update_event (e.g., for new events) or any exclusions. No alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

delete_eventB

Deletes an event from the calender.

Args: event_id: Event identifier.

ParametersJSON Schema

Name	Required	Description	Default
`event_id`	Yes

TDQS

B3.4/5.0

Behavior2/5

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 only states 'Deletes an event' without mentioning that deletion is irreversible, requiring any permissions, or detailing side effects. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and to the point, using a single sentence plus an args block. It avoids unnecessary detail, though the typo 'calender' is a minor flaw. No word is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that this is a simple one-parameter delete operation with no output schema, the description covers the core action. However, it lacks any mention of behavioral traits like irreversibility, error behavior, or return values, which are important for a delete tool, so it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has no descriptions for the event_id parameter, so the description's 'Args: event_id: Event identifier' adds some semantic value by clarifying the parameter's role. However, this is minimal and largely redundant with the parameter name and the tool's purpose, so the description does not substantially compensate for the 0% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Deletes' and the resource 'an event from the calender', making the tool's purpose unambiguous. It naturally distinguishes itself from the sibling tools list_events, create_event, and update_event, which represent different CRUD operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives. However, the purpose is self-evident from the verb and the sibling tool names, which implies that this tool is for removing events. The description does not provide any exclusions or additional context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_eventsA

Retrieve a list of calendar events based on specified filters.

This function queries the calendar for events that match the given criteria. All filter parameters are optional and can be used in combination to narrow down the results.

Args: summary (str, optional): Filter events by their summary (title or subject). description (str, optional): Filter events by text found in the event description. location (str, optional): Filter events based on their location. timeMin (str, optional): ISO 8601 formatted lower time bound (exclusive) for filtering events by end time. Must be in local time and have timezone offset. timeMax (str, optional): ISO 8601 formatted upper time bound (exclusive) for filtering events by start time. Must be in local time and have timezone offset. maxResults (int, optional): Maximum number of events to return.

Returns: list: A list of event objects that match the provided filters.

ParametersJSON Schema

Name	Required	Description	Default
`summary`	No
`timeMax`	No
`timeMin`	No
`location`	No
`maxResults`	No
`description`	No

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool queries the calendar and returns a list of matching events. It also explains the exclusive time-bound semantics and the requirement for local time with timezone offset, adding useful behavioral context beyond a simple 'list events' statement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with an introductory sentence and a clean Args list. It is appropriately sized for a tool with six parameters, and every line conveys relevant information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (six optional parameters, no output schema, no annotations), the description covers all essential aspects: parameter semantics, time format requirements, filter combination, and the return type. It provides enough information for an agent to invoke the tool correctly without further documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description fully compensates with a detailed Args section. It explains the meaning of each parameter (summary, description, location, timeMin, timeMax, maxResults) and includes format constraints, adding significant value beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Retrieve a list of calendar events based on specified filters,' which is a specific verb+resource statement. It clearly distinguishes this read-oriented list tool from sibling tools like create_event, delete_event, and update_event.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool (when retrieving filtered calendar events) and explains that filters are optional and combinable. However, it does not explicitly mention when not to use it or name alternatives, though sibling tool names make the distinction obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

update_eventA

Updates an event by replacing specified fields with new values. Any fields not included in the request will retain their existing values.

Args: event_id (str): Event identifier. start (str, optional): Event start time in ISO 8601 format (e.g., '2025-04-06T10:00:00-04:00'). Defaults to None. end (str, optional): Event end time in ISO 8601 format (e.g., '2025-04-06T11:00:00-04:00'). Defaults to None. timeZone (str, optional): User timezone formatted as an IANA Time Zone Database name (e.g. "Europe/Zurich"). Defaults to None. summary (str, optional): Short title or subject of the event. Defaults to None. description (str, optional): Detailed description or notes for the event. Defaults to None. location (str, optional): Physical or virtual location of the event. Defaults to None.

ParametersJSON Schema

Name	Required	Description	Default
`end`	No
`start`	No
`summary`	No
`event_id`	Yes
`location`	No
`timeZone`	No
`description`	No

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description must carry the transparency burden. It does disclose a key behavior: fields not included retain existing values, indicating a partial update. It also provides format details for start/end/timeZone. However, it does not mention permissions, error handling, idempotency, or what happens when setting a field to null, leaving significant behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a concise introductory sentence followed by a clean Args block. Every parameter is listed with its format and optionality. The repetition of 'Defaults to None' is minor and acceptable for readability. It is appropriately sized and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with no output schema or annotations, the description covers the core update semantics and parameter formats but lacks important context: return value, error behavior, null clearing, and prerequisites. It is adequate for basic use but not comprehensive for an agent handling edge cases or unexpected scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. The Args block provides meaningful detail beyond the schema: ISO 8601 format examples, timezone database naming, and default behavior (None). This helps an agent construct valid calls, though some inter-parameter details (e.g., timeZone applicability) are missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Updates an event by replacing specified fields with new values.' The partial-update behavior is explicitly stated, which distinguishes this from create and delete siblings. It is clear that this tool modifies an existing event.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context for using this tool is clear: it updates an existing event, as opposed to list, create, or delete. However, it does not explicitly mention alternatives or provide 'when not to use' guidance. The sibling tool names are not referenced in the description, so the guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.0Aug 1, 2026
- First observedcreate_event
- First observeddelete_event
- First observedlist_events
- First observedupdate_event

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0

Disambiguation5/5

Each tool targets a distinct operation on calendar events: listing, creating, deleting, and updating. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: list_events, create_event, delete_event, update_event. This provides a predictable and clear naming convention.

Tool Count5/5

With only 4 tools, the server is tightly focused on core calendar event operations. The count is well within the ideal range and each tool serves a necessary purpose.

Completeness4/5

The server offers full CRUD coverage for events: create, read (list), update, and delete. A minor gap is the lack of a direct 'get event by ID' operation, but list_events with filters can work around this.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Chronary A
ai.chronary
Calendar API for AI agents: events, availability, Google/Microsoft setup, scheduling, and iCal.
Calendar Management Workplace & Productivity
542
calendar-bridgeOAuth
io.github.IsaiahDupree
Connects ChatGPT to your Apple Calendar via a local Mac agent + Vercel relay
Calendar Management App Automation
1
Kalender Sync A
de.kalender-sync
GDPR-compliant calendar access for AI assistants. Google, Microsoft 365, Apple & more. EU-hosted.
Calendar Management Workplace & Productivity
71
Grounders MCPOAuth
io.github.ItsBreeze
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
1

Related MCP Servers

Google Calendar MCP Server
App Automation Calendar Management
thisnick
F
license
Not graded
quality
D
maintenance
Allows interaction with Google Calendar through Claude Desktop using the Model Context Protocol, enabling calendar event management and schedule analysis.
Updated a year ago (2025-03-07 18:23 UTC)
2
-
Google Calendar MCP Server
Calendar Management App Automation
peadams21
A
license
A
quality
D
maintenance
Provides comprehensive Google Calendar integration capabilities allowing AI assistants to list, create, update, and delete calendar events through a standardized Model Context Protocol.
Updated a year ago (2025-08-06 00:32 UTC)
5
22
MIT
Google Calendar MCP Server
Calendar Management App Automation
sohamkapileshwar2
F
license
Not graded
quality
D
maintenance
Enables natural language interaction with Google Calendar via the Model Context Protocol, allowing LLMs like Claude to read and manage calendar events through the Google Calendar v3 API.
Updated a year ago (2025-06-29 09:29 UTC)
2
-
mcp-calendar-python
Calendar Management Workplace & Productivity
tobedoit
A
license
B
quality
C
maintenance
Enables creating, modifying, and checking Google Calendar events from Claude desktop app using MCP protocol with secure OAuth2 authentication.
Updated 7 months ago (2026-02-17 01:06 UTC)
2
2
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rsc1102/Google_Calendar_MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server