Taskflow MCP Server

Model Context Protocol (MCP) server for planning and executing tasks.

Local serverstdioTypeScript

What is the Taskflow MCP server?

Taskflow MCP server exists for a simple reason — assistants are far more useful when they can act on Taskflow directly instead of describing what you should do. Model Context Protocol (MCP) server for planning and executing tasks.

What the assistant can call

Once Taskflow is connected, these are the calls the assistant has available:

  • Configuration — By default, TaskFlow MCP saves tasks to tasks.yaml in the current working directory. You can customize this by setting the TASK_MANAGER_FILE_PATH
  • plan_task — Register a new user request and plan its associated tasks (with optional subtasks)
  • get_next_task — The get_next_task tool exposed by this server
  • mark_task_done — The mark_task_done tool exposed by this server
  • open_task_details — The open_task_details tool exposed by this server
  • list_requests — The list_requests tool exposed by this server
  • add_tasks_to_request — The add_tasks_to_request tool exposed by this server
  • update_task — The update_task tool exposed by this server
  • delete_task — The delete_task tool exposed by this server
  • add_subtasks — The add_subtasks tool exposed by this server
  • mark_subtask_done — The mark_subtask_done tool exposed by this server
  • update_subtask — The update_subtask tool exposed by this server

Setting it up

taskflow-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration and credentials

You will need 4 environment variables: TASK_MANAGER_FILE_PATH, TASK_MANAGER_BASE_DIR, ARCHIVE_FILE_PATH, ARCHIVE_MODE. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Taskflow's toolset — Configuration, plan_task, get_next_task and 11 more — is a fair guide to whether it matches your workflow. It is maintained by sizzlebop; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Taskflow.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the taskflow mcp server does with a few real requests.

Available tools

ToolWhat it does
ConfigurationBy default, TaskFlow MCP saves tasks to tasks.yaml in the current working directory. You can customize this by setting the TASK_MANAGER_FILE_PATH environment variable:
plan_taskRegister a new user request and plan its associated tasks (with optional subtasks).
get_next_taskThe get_next_task tool exposed by this server.
mark_task_doneThe mark_task_done tool exposed by this server.
open_task_detailsThe open_task_details tool exposed by this server.
list_requestsThe list_requests tool exposed by this server.
add_tasks_to_requestThe add_tasks_to_request tool exposed by this server.
update_taskThe update_task tool exposed by this server.
delete_taskThe delete_task tool exposed by this server.
add_subtasksThe add_subtasks tool exposed by this server.
mark_subtask_doneThe mark_subtask_done tool exposed by this server.
update_subtaskThe update_subtask tool exposed by this server.
delete_subtaskThe delete_subtask tool exposed by this server.
export_task_statusExport the current status of all tasks in a request to a file. It's recommended to use absolute paths for more reliable file creation.

How to install the Taskflow MCP server

{
  "mcpServers": {
    "taskflow": {
      "command": "npx",
      "args": ["-y", "taskflow-mcp"],
      "env": {
        "TASK_MANAGER_FILE_PATH": "your-value",
        "TASK_MANAGER_BASE_DIR": "your-value",
        "ARCHIVE_FILE_PATH": "your-value",
        "ARCHIVE_MODE": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
TASK_MANAGER_FILE_PATHFilesystem location the server is allowed to use.Optional
TASK_MANAGER_BASE_DIRFilesystem location the server is allowed to use.Optional
ARCHIVE_FILE_PATHFilesystem location the server is allowed to use.Optional
ARCHIVE_MODEConfiguration value read at startup.Optional

Example prompts to try

  • Use Taskflow to Configuration.
  • Use Taskflow to plan task.
  • Use Taskflow to get next task.

Frequently asked questions

It connects Taskflow to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Configuration, plan_task, get_next_task, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Taskflow directly.