A task management Model Context Protocol (MCP) server that helps AI assistants break down user requests into manageable tasks with subtasks, dependencies, and notes. Enforces a structured workflow with user approval steps.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add taskflow --env TASK_MANAGER_FILE_PATH='<TASK_MANAGER_FILE_PATH>' -- npx -y @pinkpixel/taskflow-mcp~/.codex/config.toml
[mcp_servers.taskflow]
command = "npx"
args = ["-y", "@pinkpixel/taskflow-mcp"]
env = { TASK_MANAGER_FILE_PATH = "<TASK_MANAGER_FILE_PATH>" }
# codex mcp add taskflow --env TASK_MANAGER_FILE_PATH='<TASK_MANAGER_FILE_PATH>' -- npx -y @pinkpixel/taskflow-mcp~/.cursor/mcp.json
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/taskflow-mcp"
],
"env": {
"TASK_MANAGER_FILE_PATH": "<TASK_MANAGER_FILE_PATH>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"taskflow": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@pinkpixel/taskflow-mcp"
],
"env": {
"TASK_MANAGER_FILE_PATH": "<TASK_MANAGER_FILE_PATH>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/taskflow-mcp"
],
"env": {
"TASK_MANAGER_FILE_PATH": "<TASK_MANAGER_FILE_PATH>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/taskflow-mcp"
],
"env": {
"TASK_MANAGER_FILE_PATH": "<TASK_MANAGER_FILE_PATH>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"taskflow": {
"command": "npx",
"args": [
"-y",
"@pinkpixel/taskflow-mcp"
],
"env": {
"TASK_MANAGER_FILE_PATH": "<TASK_MANAGER_FILE_PATH>"
}
}
}
}Environment variables
TASK_MANAGER_FILE_PATH
Replace the placeholders with your own credentials and keep them out of version control.