Execution System MCP Server
Enables AI-native task and project management through natural language conversation with Claude, eliminating app-switching by letting you add actions, manage projects across multiple areas of focus, and maintain a GTD-style execution system directly in chat.
README
Execution System MCP Server
An AI-native execution system powered by Claude and the Model Context Protocol.
Why This Exists
Traditional productivity tools force you to context-switch between thinking and doing. You stop your work, open an app, navigate through menus, fill out forms, and then return to what you were doing. This friction means you often don't capture things at all, or you create incomplete entries that need cleanup later.
This MCP server eliminates that friction. You stay in conversation with Claude while working, and your execution system updates naturally:
- Working on code? "Add action: refactor the auth module @macbook +api-redesign due:2025-11-15"
- In a meeting? "Add to waiting: Sarah's feedback on the proposal"
- Reviewing your week? "List all actions for the ml-refresh project"
- Planning? "Show me all Health projects that haven't been reviewed in 7 days"
No app switching. No form filling. Just natural language that keeps you in flow while maintaining a rigorous execution system.
Features
The server implements the horizons of focus model through the Model Context Protocol:
0k - Next Actions (Ground Level)
- Add actions to context files (@macbook, @phone, @errands) with automatic project validation
- Add to special lists: @waiting (for others), @deferred (specific future date), @incubating (someday/maybe)
- Complete actions by line number with automatic archival to completed.md
- List actions with flexible filtering by context, project, and state
- Search actions by text with state and context filters
- Full support for todo.txt format with creation dates, contexts, projects, due/defer dates
10k - Projects (Current Initiatives)
- Create projects with YAML frontmatter and three templates (standard, coordination, habit)
- List projects with flexible filtering and grouping by area, due date, or flat
- Search projects by text in title or content
- Complete projects with validation that all actions are done
- Manage lifecycle: activate from incubator, move back to incubator, descope
- Update metadata: due dates, areas, types, review dates (bulk updates supported)
- Audit tools: validate data quality, find orphan projects/actions, identify items needing review
20k - Areas of Focus (Responsibilities)
- List areas of focus from configuration
- Automatic area validation across all projects and goals
30k - Goals (1-2 Year Objectives)
- List goals from active and incubator folders
- Automatic filtering by
type: goalin YAML frontmatter - Support for nested goal directories with supporting materials
All tools include comprehensive validation, error handling, and JSON output for programmatic access.
Installation
# Clone the repository
git clone https://github.com/elinsky/execution-system-mcp.git
cd execution-system-mcp
# Install dependencies
pip install -e ".[dev]"
Configuration
Create a configuration file at ~/.config/execution-system-mcp/config.json:
{
"execution_system_repo_path": "/absolute/path/to/your/execution-system-repo",
"areas": [
{"name": "Health", "kebab": "health"},
{"name": "Learning", "kebab": "learning"},
{"name": "Career", "kebab": "career"},
{"name": "Mission", "kebab": "mission"},
{"name": "Personal Growth Systems", "kebab": "personal-growth-systems"},
{"name": "Social Relationships", "kebab": "social-relationships"},
{"name": "Romance", "kebab": "romance"},
{"name": "Emotional Health", "kebab": "emotional-health"},
{"name": "Finance", "kebab": "finance"},
{"name": "Character and Values", "kebab": "character-and-values"},
{"name": "Hobbies and Recreation", "kebab": "hobbies-and-recreation"}
]
}
Development
# Run tests
pytest
# Run tests with coverage
pytest --cov=src --cov-report=html
# Run specific test file
pytest tests/unit/test_config.py
Usage
The MCP server integrates with Claude Desktop. Once configured, you can manage your execution system by asking Claude:
0k - Action Examples
- "Add action 'Buy groceries' to @errands context for project meal-planning"
- "Add 'Wait for package delivery' to @waiting with defer date 2025-11-15"
- "Complete the action on line 7 of contexts/@macbook.md"
- "List all actions for the ml-refresh project"
10k - Project Examples
- "Create a new project titled 'Learn Python' in the Learning area as a standard project in active folder"
- "List all active projects in the Health area"
- "Complete the project 'Learn Python'"
- "Search for projects about machine learning"
20k - Area Examples
- "List all my areas of focus"
30k - Goal Examples
- "List all active goals"
- "Show me goals in the incubator"
Claude will use the appropriate MCP tools to interact with your execution system.
Available Tools
0k - Action Tools
add_action- Add next action to context file with project validationadd_to_waiting- Add item to @waiting listadd_to_deferred- Add item to @deferred listadd_to_incubating- Add item to @incubating listcomplete_action- Complete action by line numberlist_actions- List actions with flexible filtering and groupingsearch_actions- Search actions by text with filters
10k - Project Tools
create_project- Create new project with YAML frontmatter and templatelist_active_projects- List all active projects grouped by arealist_projects- List projects with flexible filtering (folder, area, due date)complete_project- Complete project with validation for incomplete actionsactivate_project- Move project from incubator to activemove_project_to_incubator- Move project from active to incubatordescope_project- Move project to descoped folderupdate_project_due_date- Add or remove project due dateupdate_project_area- Change project's area of focusupdate_project_type- Change project type (standard/coordination/habit)update_review_dates- Bulk update last_reviewed datessearch_projects- Search projects by text with filters
20k - Area Tools
list_areas- List all configured areas of focus
30k - Goal Tools
list_goals- List goals from active and incubator folders
Audit & Health Check Tools
audit_projects- Validate project data qualityaudit_orphan_projects- Find projects without actionsaudit_orphan_actions- Find actions with invalid projects/contextsaudit_action_files- Validate action file data qualitylist_projects_needing_review- Find projects not reviewed recentlylist_actions_needing_review- Find action files not reviewed recently
Project Structure
execution-system-mcp/
├── src/
│ └── gtd_mcp/
│ ├── __init__.py
│ ├── server.py # MCP server with all tool handlers
│ ├── config.py # Configuration manager
│ ├── creator.py # Project creation
│ ├── lister.py # Project listing
│ ├── completer.py # Project completion
│ ├── validator.py # Validation logic
│ ├── templates.py # Project templates
│ ├── project_manager.py # Project lifecycle management
│ ├── action_manager.py # Action creation and completion
│ ├── action_lister.py # Action listing
│ ├── goal_lister.py # Goal listing
│ ├── area_lister.py # Area listing
│ ├── searcher.py # Search functionality
│ └── auditor.py # Data quality audits
├── tests/
│ └── unit/ # 185 comprehensive unit tests
├── pyproject.toml
└── README.md
License
MIT
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.