How is First Light different from other task managers?
First Light is built for AI interaction—tasks are created, edited, and queried directly by your assistant, with no manual data entry or middleware required.
@anytime-sync
基本情報
AI-native task manager with native MCP server. Let Claude or any MCP client read, create, update, complete, and reschedule your tasks directly — no copy-pasting. Includes semantic search, daily planning, habit tracking, and weekly reviews. Free tier available.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"firstlight": {
"command": "npx",
"args": [
"firstlight-mcp"
],
"env": {
"FIRSTLIGHT_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Get tasks by date, status, or priority
Add task with title, date, priority, notes
Edit any field on an existing task
Mark a task as done
Remove a task
AI-reorganize today's schedule
Semantic search across all tasks
Check habit streaks and progress
Generate a summary of your week
An AI-native task manager that integrates with the Model Context Protocol (MCP), allowing AI assistants to manage tasks directly without copy-pasting or middleware. Designed for users of MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.
Obtain an API token from firstlight.to (Settings → API Tokens), add the configuration to your MCP client, then start giving natural language commands (e.g., “What’s on my plate today?”).
First Light is built for AI interaction—tasks are created, edited, and queried directly by your assistant, with no manual data entry or middleware required.
You need an API token from firstlight.to and an MCP-compatible client such as Claude Desktop, Cursor, or Windsurf.
Tasks are stored on the First Light service. Your API token authenticates access.
Yes, it uses API token–based authentication. The transportation is handled via the MCP protocol; no additional transport details are specified in the README.
The README does not list any specific limitations.
不止于 CSS
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Painless E2E Automation for Mobile and Web
Hindsight: Agent Memory That Learns
A search tool helps dev to solve the naming things problem.
コメント