
GitHub Calendar MCP Server
Enables AI assistants to interact with GitHub project boards as calendar events, analyze team workloads, and provide scheduling insights. Supports team status tracking, workload distribution analysis, and smart task assignment recommendations.
README
GitHub Calendar MCP Server
A Model Context Protocol (MCP) server that provides GitHub project calendar and team management capabilities. This server allows AI assistants like Goose to interact with GitHub project boards, analyze team workloads, and provide scheduling insights.
Features
- 📅 Calendar Events: Fetch GitHub project issues as calendar events
- 👥 Team Status: Get current status of all team members
- 📊 Workload Analysis: Analyze team workload distribution
- 🎯 Smart Assignment: Find the best team member for new tasks
- 📋 Personal Schedules: Get individual team member schedules
- 🔍 Flexible Filtering: Filter by organization, project, dates, and assignees
Installation
-
Clone or create the project directory:
mkdir github-calendar-mcp-server cd github-calendar-mcp-server
-
Install dependencies:
npm install
-
Set up environment variables: Create a
.env
file or set environment variables:export GITHUB_TOKEN=your_github_personal_access_token
To create a GitHub token:
- Go to GitHub Settings → Developer settings → Personal access tokens
- Create a new token with these permissions:
repo
(for private repositories)read:org
(for organization data)read:project
(for project boards)
Usage
Running the Server
npm start
The server will start and listen for MCP connections on stdio.
Integration with Goose
Add this configuration to your Goose MCP settings:
{
"mcpServers": {
"github-calendar": {
"command": "node",
"args": ["/full/path/to/github-calendar-mcp-server/index.js"],
"env": {
"GITHUB_TOKEN": "your_github_token_here"
}
}
}
}
Available Tools
1. get_team_status
Get current status of all development team members.
Example prompts:
- "What's the current team status?"
- "Show me how busy everyone is"
- "Get team workload overview"
2. get_person_schedule
Get schedule for a specific team member.
Parameters:
login
(required): GitHub usernamedays
(optional): Number of days to look ahead (default: 7)
Example prompts:
- "What's Alice's schedule for the next week?"
- "Show me Bob's upcoming work for the next 14 days"
3. analyze_workload
Analyze team workload distribution.
Example prompts:
- "Analyze the team workload"
- "Who has the most/least work?"
- "Show me workload distribution"
4. find_best_assignee
Find the team member with the lightest workload.
Example prompts:
- "Who should I assign this new task to?"
- "Find the best person for a new assignment"
- "Who has the lightest workload?"
5. get_calendar_events
Get GitHub project calendar events with filtering options.
Parameters:
org
(optional): GitHub organization (default: "squareup")project
(optional): Project number (default: 333)since
(optional): ISO date string to filter from (default: "2025-08-01")assignee
(optional): Filter by GitHub username
Example prompts:
- "Show me all calendar events"
- "Get events for Alice"
- "Show me events since September 2025"
- "Get calendar events for the design team project"
Configuration
The server is pre-configured for:
- Organization:
squareup
- Project:
333
- Label Filter:
area: devrel-opensource
- Date Range: From August 2025 onwards
You can modify these defaults in the index.js
file:
const DEFAULT_ORG = 'your-org';
const DEFAULT_PROJECT_NUMBER = 123;
const DEFAULT_LABEL = 'your-label';
Data Sources
The server fetches data from:
- GitHub Projects v2 API (GraphQL) - Primary source
- GitHub Search API - Fallback if GraphQL fails
- Issue custom fields - For start/end dates
- Issue body parsing - Backup date extraction
- Milestone due dates - Additional date source
Error Handling
The server includes comprehensive error handling:
- Authentication errors: Clear messages about GitHub token issues
- API rate limits: Graceful handling of GitHub API limits
- Network issues: Fallback between GraphQL and REST APIs
- Missing data: Sensible defaults for incomplete information
Example Interactions
You: "What's the team status?"
Goose: "Here's the current team status:
**alice**
- Active Issues: 3
- Upcoming Issues: 1
- Overdue Issues: 0
- Total Workload: 4
**bob**
- Active Issues: 1
- Upcoming Issues: 2
- Overdue Issues: 1
- Total Workload: 4"
You: "Who should I assign a new task to?"
Goose: "**alice** has the lightest workload:
- Current workload: 2 issues
- Active: 2
- Upcoming: 0
- Overdue: 0"
You: "Show me Bob's schedule for next week"
Goose: "# Schedule for bob (Next 7 days)
**Fix login bug** (open)
- Start: Sep 23, 2025
- End: Sep 25, 2025
- URL: https://github.com/org/repo/issues/123"
Troubleshooting
Common Issues
-
"Authentication failed" error:
- Verify your
GITHUB_TOKEN
is set correctly - Check that the token has required permissions
- Ensure the token hasn't expired
- Verify your
-
"Project not found" error:
- Verify the organization and project number
- Check that your token has access to the project
- Ensure the project exists and is accessible
-
"No events found" error:
- Check the date range (default starts from Aug 2025)
- Verify the label filter matches your issues
- Ensure issues exist with the specified criteria
-
Server doesn't start:
- Run
npm install
to ensure dependencies are installed - Check Node.js version (requires 16+)
- Verify the
index.js
file has execute permissions
- Run
Debug Mode
For debugging, you can add console logging by modifying the server code or checking the error output when running the server.
Development
To extend the server:
- Add new tools: Modify the
setupToolHandlers()
method - Add new data sources: Extend the GitHub API integration
- Add UI components: Integrate with
@mcp-ui/server
for interactive interfaces - Add caching: Implement Redis or file-based caching for better performance
License
MIT License - feel free to modify and distribute as needed.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。