// SCAN REPORT

Agentic Tools MCP Server

29 tools. 16 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

16 can modify or destroy data

13 read-only

29 tools total

Community server · catalogue entry verified 11/06/2026

How to control Agentic Tools MCP Server ↓

TOOL MAP

Read (13) Write / Execute (12) Destructive / Financial (4)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High delete_memory Deletion is an irreversible operation that removes data and cannot be undone. Destructive · High delete_project This tool irreversibly deletes data at scale—an entire project plus all dependent tasks and subtasks. Destructive · High delete_subtask The tool performs an irreversible deletion of a subtask with no undo capability. Destructive · High delete_task This tool permanently removes data without possibility of recovery.

16 of Agentic Tools MCP Server's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL AGENTIC TOOLS MCP SERVER

PolicyLayer is an MCP gateway — it sits between your AI agents and Agentic Tools MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_memory": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "parse_prd": {
    "limits": [
      {
        "counter": "parse_prd_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_task_complexity": {
    "limits": [
      {
        "counter": "analyze_task_complexity_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Agentic Tools MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AGENTIC TOOLS →

Free to start. No card required.

ALL 29 AGENTIC TOOLS MCP SERVER TOOLS

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 and

WRITE 11 tools

Write parse_prd Parse a Product Requirements Document (PRD) and automatically generate structured tasks with dependencies, pri 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 subtask Write migrate_subtasks Migrate existing subtasks to the unified task model. This tool converts all subtasks to tasks with parentId fo Write move_task Move a task to a different parent in the hierarchy. Set newParentId to move under another task, or leave empty 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, dependencie

READ 13 tools

Read analyze_task_complexity Analyze task complexity and suggest breaking down overly complex tasks into smaller, manageable subtasks. Inte 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, an 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 for 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 to Read infer_task_progress Analyze the codebase to infer which tasks appear to be completed based on code changes, file creation, and imp

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the Agentic Tools MCP Server MCP server? +

Yes. The Agentic Tools MCP Server server exposes 4 destructive tools including delete_memory, delete_project, delete_subtask. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Agentic Tools MCP Server? +

The Agentic Tools MCP Server server has 11 write tools including parse_prd, create_memory, create_project. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Agentic Tools MCP Server.

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

29 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 16 can modify, create, or delete data.

How do I enforce a policy on Agentic Tools MCP Server? +

Register the Agentic Tools MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

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.

ENFORCE POLICY ON AGENTIC TOOLS →

Free to start. No card required.

29 Agentic Tools MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Agentic Tools MCP Server

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL AGENTIC TOOLS MCP SERVER

// ALL 29 AGENTIC TOOLS MCP SERVER TOOLS

// RELATED SERVERS

// FAQ