Agent Setup
Configure TaskFlow with your AI coding agent
Supported Agents
TaskFlow works with any MCP-compatible AI agent. Install the MCP server once, then configure your agent of choice.
bash
1npm install -g @dalmasonto/taskflow-mcpQuick Comparison
| Agent | Config Format | Config Path | Auto-Approve |
|---|---|---|---|
| Claude Code | JSON | ~/.mcp.json or .mcp.json | settings.json allow list |
| Codex CLI | TOML | ~/.codex/config.toml | Top-level approval_policy |
| Cursor | JSON | ~/.cursor/mcp.json | Settings UI toggle |
| Windsurf | JSON | ~/.codeium/windsurf/mcp_config.json | alwaysAllow array |
| Cline | JSON | VS Code global storage | alwaysAllow array |
| Continue | YAML/JSON | .continue/mcpServers/ | Agent mode only |
| GitHub Copilot | JSON | ~/.copilot/mcp-config.json | tools array |
How It Works
Every agent communicates with TaskFlow via the Model Context Protocol (MCP) over stdio:
- Your agent starts the
taskflow-mcpprocess - The MCP server exposes 50 tools (tasks, projects, timers, analytics, etc.)
- The agent calls
get_agent_instructionsorbootstrapon startup to learn the workflow - From there, the agent autonomously creates tasks, tracks time, and logs progress
No prompt engineering needed - the instructions are built into the server.