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., "@Task Manager add a task to review the quarterly report by Friday"
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.
A small Model Context Protocol (MCP) server that manages a simple tasks.json file.
Run with Bun (recommended):
bunx @abyssbug/task-manager --tasks-file ~/Documents/tasks.jsonOr set the path via env (defaults to ~/Documents/tasks.json if omitted):
TASK_MANAGER_FILE_PATH=/Users/you/Documents/tasks.json bunx @abyssbug/task-managerUsing npx is acceptable if Bun is installed (the binary uses a Bun shebang):
npx -y @abyssbug/task-manager --tasks-file ~/Documents/tasks.jsonRelated MCP server: Task Manager MCP Server
For generic MCP clients (~/.mcp/servers.json):
{
"mcpServers": {
"task-manager": {
"command": "bunx",
"args": ["@abyssbug/task-manager", "--tasks-file", "/Users/you/Documents/tasks.json"]
}
}
}For Cursor (~/.cursor/mcp.json):
{
"task-manager": {
"command": "bunx",
"args": ["@abyssbug/task-manager", "--tasks-file", "/Users/you/Documents/tasks.json"],
"working_directory": "/Users/you/Documents"
}
}The server can run over HTTP when MCP_TRANSPORT=http.
Endpoints:
GET /health → { ok: true }
GET /tools → JSON tool list
POST /call → Body: { "name": "tool_name", "arguments": { ... } }
Run locally in HTTP mode with Bun:
MCP_TRANSPORT=http PORT=3000 bun run dev
# then in another terminal
curl http://localhost:3000/health
curl http://localhost:3000/tools
curl -X POST http://localhost:3000/call -H 'content-type: application/json' -d '{"name":"list_requests","arguments":{}}'This server cannot be deployed
Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.
AI-native task management: list, create, update and archive tasks with rich context for AI agents
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.