MCP Todo & Context Server
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., "@MCP Todo & Context ServerGet a project summary for my-app with recent notes and open todos"
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.
MCP Todo & Context Server
A lightweight backend service that provides AI clients with two core capabilities:
Todo Management: Create, list, complete, and delete todo items per project
Project Context: Record and retrieve running context notes about a project's state
Features
β Per-project todo lists with priority levels
π Append-only context notes for tracking project state
π Resume work summaries (status + recent notes + open todos)
π MCP (Model Context Protocol) endpoint for AI clients
πΎ Persistent JSON file storage
π Single-instance deployment with FastAPI + uvicorn
Related MCP server: barrydo
Architecture
mcp-todo-context-server/
βββ app.py # FastAPI entry point - mounts /mcp and /health
βββ server.py # FastMCP instance + tool definitions
βββ storage.py # Persistence layer - reads/writes data.json
βββ data/
β βββ data.json # Runtime data file (auto-created)
βββ requirements.txt
βββ README.mdInstallation
1. Create Virtual Environment
python -m venv venv2. Activate Virtual Environment
Windows (PowerShell):
.\venv\Scripts\activate.ps1Windows (CMD):
venv\Scripts\activate.batLinux/Mac:
source venv/bin/activate3. Install Dependencies
pip install -r requirements.txtRunning the Server
Development Mode (with auto-reload)
python app.pyOr using uvicorn directly:
uvicorn app:app --reload --host 0.0.0.0 --port 8000Production Mode
uvicorn app:app --host 0.0.0.0 --port 8000The server will be available at:
MCP endpoint:
http://localhost:8000/mcpHealth check:
http://localhost:8000/healthAPI docs:
http://localhost:8000/docs
MCP Tools
The server exposes the following tools via the MCP protocol:
Todo Management
create_todo - Create a new todo item
project_name(required): Project identifiertitle(required): Todo titledescription(optional): Detailed descriptionpriority(optional): low/medium/high (default: medium)
list_todos - List todos for a project
project_name(required): Project identifierfilter_status(optional): 'open', 'done', or None for all
complete_todo - Mark a todo as complete
project_name(required): Project identifiertodo_id(required): Todo ID to complete
delete_todo - Delete a todo permanently
project_name(required): Project identifiertodo_id(required): Todo ID to delete
Project Context
append_context_note - Add a context note to project history
project_name(required): Project identifiernote(required): Context note textstatus(optional): Update project status label
get_project_summary - Get resume-work summary
project_name(required): Project identifierrecent_notes_count(optional): Number of recent notes (default: 10)Returns: status, recent notes, and all open todos
Project Directory
list_projects - List all projects
No parameters required
Returns: All projects with status and open todo counts
Connecting AI Clients
Claude Desktop Configuration
Add to your Claude Desktop MCP settings:
{
"mcpServers": {
"todo-context": {
"command": "uvicorn",
"args": ["app:app", "--host", "localhost", "--port", "8000"],
"cwd": "/path/to/mcp-todo-context-server",
"env": {
"VIRTUAL_ENV": "/path/to/mcp-todo-context-server/venv"
}
}
}
}Data Storage
Data is stored in data/data.json with the following structure:
{
"projects": {
"project-name": {
"name": "project-name",
"status": "active",
"context_log": [
{
"timestamp": "2026-08-13T10:30:00.000Z",
"note": "Implemented user authentication"
}
],
"todos": [
{
"id": "20260813103000123456",
"title": "Add password reset",
"description": "Implement email-based password reset flow",
"priority": "high",
"done": false,
"created": "2026-08-13T10:30:00.000Z",
"completed": null
}
]
}
}
}Example Usage
Creating a Todo
# Via MCP tool call
{
"tool": "create_todo",
"arguments": {
"project_name": "my-app",
"title": "Implement user authentication",
"description": "Add JWT-based auth with refresh tokens",
"priority": "high"
}
}Getting Project Summary
# Via MCP tool call
{
"tool": "get_project_summary",
"arguments": {
"project_name": "my-app",
"recent_notes_count": 5
}
}Response includes:
Current project status
5 most recent context notes
All open todos
Metadata (counts, timestamps)
API Endpoints
GET /- Service informationGET /health- Health checkGET /docs- Interactive API documentation (Swagger UI)POST /mcp- MCP protocol endpoint
Requirements
Python 3.8+
FastAPI
uvicorn
fastmcp (FastMCP - Model Context Protocol SDK)
pydantic
python-dotenv
Roadmap
v1.0 (Current)
β MCP endpoint with 7 tools
β JSON file storage
β Direct uvicorn deployment
Future Considerations
SQLite/PostgreSQL backend option
Authentication/authorization layer
Docker containerization
Multi-user support
Tags/categories for context notes
Due dates and reminders for todos
License
MIT License - see LICENSE file for details
Contributing
Contributions welcome! Please open an issue or PR.
Support
For issues or questions, please open a GitHub issue.
This server cannot be deployed
Maintenance
Related MCP Connectors
Project management shared by people and AI agents, with persistent project state through MCP.
Project management MCP for AI agents with safe task reads and writes.
Cross-tool persistent memory and context for AI assistants over MCP.
- TaprootOAuthcom.taproothq
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides persistent, multi-project memory for AI agents via MCP, enabling them to store and retrieve tasks, decisions, errors, checkpoints, and documentation while keeping context isolated by project.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create, read, and manage tasks and projects in a personal todo system through MCP tools.MIT
- FlicenseNot gradedqualityBmaintenanceA persistent Todo/Done workspace with REST API and MCP endpoint for task management. Enables humans and MCP agents to create, update, and complete tasks with semantic tools.-
- AlicenseBqualityCmaintenanceProvides AI agents with durable, searchable project memory, session notes, skills, and bounded context packs over MCP while leaving orchestration to the client.15MIT