TASKFLOW TOOLS

50 tools from the Taskflow MCP Server, categorised by risk level.

READ 29 tools
Read ask_agent Ask another agent a question and wait for their response. Like ask_user but targets an agent. Returns the m... Read ask_user Post a question to the TaskFlow Agent Inbox for the user to answer remotely. Returns immediately with the m... Read bootstrap **CALL THIS FIRST.** One-shot startup: returns your agent instructions, active project (auto-detected from ... Read capture_terminal Capture the current terminal content of an agent's tmux pane. Returns the visible text on screen. Useful fo... Read check_broadcast Check the status of a broadcast message — shows which agents have responded and their answers. Read check_messages Check for incoming messages from users or other agents addressed to this agent. Read check_response Check if a previously posted question (via ask_user or ask_agent) has been answered. Returns the response i... Read compact_activity_log Compact old activity log entries into a summary. Keeps the most recent entries (default 50) and summarizes ... Read get_activity_log Retrieve recent activity log entries. Shows what has changed — task completions, timer events, status trans... Read get_agent_instructions **Call this at the start of every conversation.** Returns onboarding instructions, behavioral rules, and li... Read get_analytics Get a high-level analytics summary: total focused time, task completion rates, status distribution, and tim... Read get_checkpoint Get the latest checkpoint for a task. Returns the full task snapshot — useful for resuming work after an in... Read get_project Get a project by ID with all its tasks. Use this to understand the full scope of a project before starting ... Read get_setting Get a setting value by key. Server settings (port, host, databasePath, logLevel, agentLivenessInterval, max... Read get_task Get a task by ID with time tracking info. Read the description carefully — it often contains implementation... Read get_task_cost Get per-task cost metrics: tool calls made during active timer sessions, total execution time, and tool bre... Read get_timeline Get focused time grouped by day or week. Use for visualizing work patterns over time. Read get_tool_stats Get tool execution statistics: call count, success rate, average duration per tool. Shows which tools are u... Read list_agents List registered agents with their status, project path, and connection info. Read list_checkpoints List all available checkpoints for a task. Read list_notifications List notifications. Check with unread_only=true at conversation start to surface important updates for the ... Read list_projects List all projects with task count. Call this at conversation start to understand the workspace. Read list_sessions List timer sessions with optional filters. Use to review time spent on a task or across a date range. Read list_tasks List tasks with optional filters. Use at conversation start to see what is in progress or blocked. Filter b... Read log_debug Log a debug entry to the activity log. Use this to record your work process — what you investigated, comman... Read pause_timer Pause the active timer session for a task. Call when switching context or waiting for user input. The task ... Read respond_to_message Respond to a pending message addressed to this agent. Use check_messages to see incoming messages, then res... Read search_projects Search projects by name or description. Use this to find projects related to your current work. Read search_tasks Search tasks by title or description. Use this to find tasks related to your current work before creating d...
WRITE 14 tools
Write broadcast_agents Send a question to multiple agents simultaneously. Creates a group message — each agent gets their own copy... Write bulk_create_tasks Create multiple tasks in a single transaction. Useful when breaking down a feature into subtasks. Write create_checkpoint Create a checkpoint snapshot of a task's current state. Captures: task data, dependencies, recent activity,... Write create_project Create a new project. Projects group related tasks and track time across them. Write create_task Create a new task. Use this when starting new work to keep TaskFlow in sync. Supports dependencies, tags, l... Write mark_all_notifications_read Mark all unread notifications as read. Call after the user has been briefed on pending notifications. Write mark_notification_read Mark a notification as read after surfacing it to the user. Write register_agent Register this agent with a custom name. Optional — agents auto-register on startup using the project folder... Write send_keys Send raw keystrokes to an agent's tmux pane. Use this to respond to interactive prompts (yes/no, numbered c... Write send_to_agent Send a message to another agent by name. Returns immediately. The recipient agent will receive the message ... Write update_project Update project fields such as name, color, type, or description. Write update_setting Update a setting value. Server settings (port, host, databasePath, logLevel, agentLivenessInterval, maxPort... Write update_task Update task fields. Use this to add details, update descriptions with progress notes, or adjust priority as... Write update_task_status Update task status with transition validation. Use when a task becomes blocked, is partially done, or needs...

The managed route: connect Taskflow through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @dalmasonto/taskflow-mcp
How many tools does the Taskflow MCP server have? +

The Taskflow MCP server exposes 50 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Taskflow tools? +

Route the Taskflow server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Taskflow tools fall into? +

Taskflow tools are categorised as Read (29), Write (14), Destructive (5), Execute (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.