// MCP TOOL REFERENCE

AGENTIC TOOLS MCP SERVER TOOLS

29 tools from the Agentic Tools MCP Server MCP Server, categorised by risk level.

View the Agentic Tools MCP Server policy →

// ALL 29 AGENTIC TOOLS MCP SERVER TOOLS

READ 13 tools

Read analyze_task_complexity Analyze task complexity and suggest breaking down overly complex tasks into smaller, manageable subtasks. I... Read get_memory Get a specific memory by its ID Read get_next_task_recommendation Get intelligent recommendations for the next task to work on based on dependencies, priorities, complexity,... Read get_project Get detailed information about a specific project by its ID Read get_subtask Get detailed information about a specific subtask by its ID Read get_task Get detailed information about a specific task by its ID Read list_memories List memories with optional filtering by category and limit Read list_projects View all projects in the task management system Read list_subtasks View subtasks, optionally filtered by task ID or project ID Read list_tasks View tasks in hierarchical tree format. Filter by projectId (required) and/or parentId. Use parentId=null f... Read search_memories Search memories by text content matching Read generate_research_queries Generate intelligent, targeted web search queries for task research. Provides structured search strategies ... Read infer_task_progress Analyze the codebase to infer which tasks appear to be completed based on code changes, file creation, and ...

WRITE 11 tools

Write parse_prd Parse a Product Requirements Document (PRD) and automatically generate structured tasks with dependencies, ... Write create_memory Create a new memory in the agent memories system Write create_project Create a new project in the task management system Write create_subtask Create a new subtask within a specific task Write create_task Create a new task within a specific project. Supports unlimited nesting depth - set parentId to create subt... Write migrate_subtasks Migrate existing subtasks to the unified task model. This tool converts all subtasks to tasks with parentId... Write move_task Move a task to a different parent in the hierarchy. Set newParentId to move under another task, or leave em... Write update_memory Update an existing memory\ Write update_project Update the name and/or description of an existing project Write update_subtask Update the name, details, and/or completion status of an existing subtask Write update_task Update task properties including name, details, parent relationship (parentId), completion status, dependen...

DESTRUCTIVE 4 tools

Destructive delete_memory Delete a memory by ID (requires confirmation) Destructive delete_project Delete a project and all its associated tasks and subtasks. This action cannot be undone. Destructive delete_subtask Delete a subtask. This action cannot be undone. Destructive delete_task Delete a task and all its associated subtasks. This action cannot be undone.

EXECUTE 1 tools

Execute research_task Guide the AI agent to perform comprehensive web research for a task, with intelligent research suggestions ...

// FAQ

How many tools does the Agentic Tools MCP Server MCP server have? +

The Agentic Tools MCP Server MCP server exposes 29 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Agentic Tools MCP Server tools? +

Route the Agentic Tools MCP Server 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 Agentic Tools MCP Server tools fall into? +

Agentic Tools MCP Server tools are categorised as Read (13), Write (11), Destructive (4), Execute (1). Each category has a recommended default policy.

Enforce policy on every Agentic Tools MCP Server tool call.

Deterministic rules across all 29 Agentic Tools MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN AGENTIC TOOLS →

Free to start. No card required.

42,500+ MCP servers and 110,000+ tools scanned and risk-classified.