by robertn702
Discover the best app planner for daily tasks with Sunsama. Organize and manage tasks using the planner app best suited
Connects AI assistants to Sunsama's task management platform to create, update, and organize tasks through the Sunsama API.
Sunsama is a community-built MCP server published by robertn702 that provides AI assistants with tools and capabilities via the Model Context Protocol. Discover the best app planner for daily tasks with Sunsama. Organize and manage tasks using the planner app best suited It is categorized under productivity.
You can install Sunsama in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Sunsama is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Sunsama reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
According to our notes, Sunsama benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
According to our notes, Sunsama benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
We wired Sunsama into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Useful MCP listing: Sunsama is the kind of server we cite when onboarding engineers to host + tool permissions.
Strong directory entry: Sunsama surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Strong directory entry: Sunsama surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Useful MCP listing: Sunsama is the kind of server we cite when onboarding engineers to host + tool permissions.
I recommend Sunsama for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
According to our notes, Sunsama benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
showing 1-10 of 62
A Model Context Protocol (MCP) server that provides comprehensive task management capabilities through the Sunsama API. This server enables AI assistants to access Sunsama tasks, create new tasks, mark tasks complete, and manage your productivity workflow.
<a href="https://glama.ai/mcp/servers/@robertn702/mcp-sunsama"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@robertn702/mcp-sunsama/badge" /> </a>No installation required! Use directly with:
npx mcp-sunsama
git clone https://github.com/robertn702/mcp-sunsama.git
cd mcp-sunsama
bun install
cp .env.example .env
# Edit .env and add your Sunsama credentials
Environment variables:
SUNSAMA_EMAIL - Your Sunsama account email (required for stdio transport)SUNSAMA_PASSWORD - Your Sunsama account password (required for stdio transport)TRANSPORT_MODE - Transport type: stdio (default) or httpPORT - Server port for HTTP transport (default: 8080)HTTP_ENDPOINT - MCP endpoint path (default: /mcp)SESSION_TTL - Session timeout in milliseconds (default: 3600000 / 1 hour)CLIENT_IDLE_TIMEOUT - Client idle timeout in milliseconds (default: 900000 / 15 minutes)MAX_SESSIONS - Maximum concurrent sessions for HTTP transport (default: 100)This server supports two transport modes:
For local AI assistants (Claude Desktop, Cursor, etc.):
bun run dev
# or
TRANSPORT_MODE=stdio bun run src/main.ts
For remote access and web-based integrations:
TRANSPORT_MODE=http PORT=8080 bun run src/main.ts
HTTP Endpoints:
POST http://localhost:8080/mcpGET http://localhost:8080/Authentication: HTTP requests require HTTP Basic Auth with your Sunsama credentials:
curl -X POST http://localhost:8080/mcp \
-H "Authorization: Basic $(echo -n 'your-email:your-password' | base64)" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
Add this configuration to your Claude Desktop MCP settings:
{
"mcpServers": {
"sunsama": {
"command": "npx",
"args": ["mcp-sunsama"],
"env": {
"SUNSAMA_EMAIL": "[email protected]",
"SUNSAMA_PASSWORD": "your-password"
}
}
}
}
Add the Sunsama MCP server using the Claude Code CLI:
claude mcp add sunsama --scope user \
-e [email protected] \
-e SUNSAMA_PASSWORD=your-password \
-- npx mcp-sunsama
Scope Options:
--scope user - Available across all projects (recommended)--scope project - Only available in the current projectAfter adding the server, restart Claude Code to connect to the Sunsama MCP server.
create-task - Create new tasks with optional properties including GitHub issue/PR and Gmail integrationget-tasks-by-day - Get tasks for a specific day with completion filteringget-tasks-backlog - Get backlog tasksget-archived-tasks - Get archived tasks with pagination (includes hasMore flag for LLM context)get-task-by-id - Get a specific task by its IDupdate-task-complete - Mark tasks as completeupdate-task-planned-time - Update the planned time (time estimate) for tasksupdate-task-notes - Update task notes content (requires either html or markdown parameter, mutually exclusive)update-task-due-date - Update the due date for tasks (set or clear due dates)update-task-text - Update the text/title of tasksupdate-task-stream - Update the stream/channel assignment for tasksupdate-task-snooze-date - Reschedule tasks to different datesupdate-task-backlog - Move tasks to the backlogdelete-task - Delete tasks permanentlyadd-subtask - Create a subtask with a title in one call (recommended for single subtask creation)create-subtasks - Create multiple subtasks for a task (low-level API for bulk operations)update-subtask-title - Update the title of a subtaskcomplete-subtask - Mark a subtask as complete with optional completion timestampuncomplete-subtask - Mark a subtask as incompleteget-user - Get current user informationget-streams - Get streams/channels for project organizationThe create-task tool supports linking tasks to external services like GitHub and Gmail.
Link a task to a GitHub issue:
{
"text": "Fix authentication bug",
"integration": {
"service": "github",
"identifier": {
"id": "I_kwDOO4SCuM7VTB4n",
"repositoryOwnerLogin": "robertn702",
"repositoryName": "mcp-sunsama",
"number": 42,
"type": "Issue",
"url": "https://github.com/robertn702/mcp-sunsama/issues/42",
"__typename": "TaskGithubIntegrationIdentifier"
},
"__typename": "TaskGithubIntegration"
}
}
Link a task to a GitHub pull request:
{
"text": "Review API refactoring PR",
"integration": {
"service": "github",
"identifier": {
"id": "PR_kwDOO4SCuM7VTB5o",
"repositoryOwnerLogin": "robertn702",
"repositoryName": "mcp-sunsama",
"number": 15,
"type": "PullRequest",
"url": "https://github.com/robertn702/mcp-sunsama/pull/15",
"__typename": "TaskGithubIntegrationIdentifier"
},
"__typename": "TaskGithubIntegration"
}
}
Link a task to a Gmail email:
{
"text": "Respond to project update email",
"integration": {
"service": "gmail",
"identifier": {
"id": "19a830b40fd7ab7d",
"messageId": "19a830b40fd7ab7d",
"accountId": "[email protected]",
"url": "https://mail.google.com/mail/u/[email protected]/#inbox/19a830b40fd7ab7d",
"__typename": "TaskGmailIntegrationIdentifier"
},
"__typename": "TaskGmailIntegration"
}
}
Note: All integration parameters are optional. Tasks can be created without integrations for standard task management.
bun run dev
bun run inspect
Then connect the MCP Inspector to test the tools interactively.
bun test # Run unit tests only
bun test:unit # Run unit tests only (alias)
bun test:integration # Run integration tests (requires credentials)
bun test:all # Run all tests
bun test:watch # Watch mode for unit tests
bun run build # Compile TypeScript to dist/
bun run typecheck # Run TypeScript type checking
bun run typecheck:watch # Watch mode type checking
For information on creating releases and publishing to npm, see CONTRIBUTING.md.
The server is organized with a modular, resource-based architecture:
src/
├── tools/
│ ├── shared.ts # Common utilities and patterns
│ ├── user-tools.ts # User operations (get-user)
│ ├── task-tools.ts # Task operations (15 tools)
│ ├── stream-tools.ts # Stream operations (get-streams)
│ └── index.ts # Export all tools
├── resources/
│ └── index.ts # API documentation resource
├── auth/ # Authentication strategies
│ ├── stdio.ts # Stdio transport authentication
│ ├── http.ts # HTTP Basic Auth parsing
│ └── types.ts # Shared auth types
├── transports/
│ ├── stdio.ts # Stdio transport implementation
│ └── http.ts # HTTP Stream transport with session management
├── session/
│ └── session-manager.ts # Session lifecycle management
├── config/ # Environment configuration
│ ├── transport.ts # Transport mode configuration
│ └── session-config.ts # Session TTL configuration
├── utils/ # Utilities (filtering, trimming, etc.)
│ ├── client-resolver.ts # Transport-agnostic client resolution
│ ├── task-filters.ts # Task completion filtering
│ ├── task-trimmer.ts # Response size optimization
│ └── to-tsv.ts # TSV formatting utilities
├── schemas.ts # Zod validation schemas
└── main.ts # Server setup (47 lines vs 1162 before refactoring)
__tests__/
├── unit/ # Unit tests (no auth required)
│ ├── auth/ # Auth utility tests
│ ├── config/ # Configuration tests
│ └── session/ # Session management tests
└── integration/ # Integration tests (requires credentials)
└── http-transport.test.ts
Key Features:
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.