// SCAN REPORT

TasksMultiServer

23 tools. 15 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

15 can modify or destroy data

8 read-only

23 tools total

Community server · catalogue entry verified 04/07/2026

How to control TasksMultiServer ↓

TOOL MAP

What TasksMultiServer exposes to your agents

Read (8) Write / Execute (13) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous TasksMultiServer tools

Destructive · High delete_project This tool permanently and irreversibly removes an entire project including all nested task lists and tasks. Destructive · High delete_task_list This tool irreversibly removes a task list and cascades deletion to all contained tasks. Write · Low remove_task_tags Removing tags alters task metadata but does not delete the task itself or cause irreversible data loss. Write · Low add_execution_note The tool adds a note to a task, which is a non-destructive write operation.

15 of TasksMultiServer's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control TasksMultiServer

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

Deny destructive operations

{
  "delete_project": {
    "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

{
  "add_execution_note": {
    "limits": [
      {
        "counter": "add_execution_note_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_dependencies": {
    "limits": [
      {
        "counter": "analyze_dependencies_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 TasksMultiServer — 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 TASKSMULTISERVER →

Instant setup, no code required.

FULL CATALOGUE

All 23 TasksMultiServer tools

DESTRUCTIVE 2 tools

Destructive delete_project Delete a project and all its task lists and tasks. Default projects (Chore, Repeatable) cannot be deleted. Destructive delete_task_list Delete a task list and all its tasks

WRITE 13 tools

Write add_execution_note Add an execution note to a task Write add_research_note Add a research note to a task Write add_task_note Add a general note to a task Write add_task_tags Add tags to a task with validation and deduplication. Tags are labels for categorization and filtering. Write create_project Create a new project with a name and optional agent instructions template Write create_task Create a new task with all required fields (title, description, status, dependencies, exit_criteria, priority, Write create_task_list Create a new task list with project assignment logic. If repeatable=true, assigns to Write remove_task_tags Remove tags from a task. Tags that don Write update_action_plan Update the action plan for a task (replaces existing action plan) Write update_exit_criteria Update exit criteria for a task, marking individual criteria as COMPLETE or INCOMPLETE Write update_project Update an existing project Write update_task_dependencies Update task dependencies with circular dependency validation Write update_task_status Update task status with exit criteria validation (cannot mark COMPLETED unless all exit criteria are COMPLETE)

READ 8 tools

Read analyze_dependencies Analyze task dependencies within a scope (project or task list). Returns critical path, bottlenecks, leaf task Read get_agent_instructions Generate agent instructions for a task using template resolution hierarchy (task → task list → project → fallb Read get_project Retrieve a project by its ID or name Read get_ready_tasks Retrieve tasks that are ready for execution (tasks with no pending dependencies or all dependencies completed) Read get_task_list Retrieve a task list by its ID, including all its tasks Read list_projects List all projects in the task management system, including default projects (Chore and Repeatable) Read search_tasks Search and filter tasks by multiple criteria including text query, status, priority, tags, and project. Suppor Read visualize_dependencies Generate a visualization of task dependencies within a scope (project or task list). Supports ASCII art, Graph

EXPLORE

Related servers

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

FAQ

Questions about TasksMultiServer

Can an AI agent delete data through the TasksMultiServer MCP server? +

Yes. The TasksMultiServer server exposes 2 destructive tools including delete_project, delete_task_list. 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 TasksMultiServer? +

The TasksMultiServer server has 13 write tools including add_execution_note, add_research_note, add_task_note. 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 TasksMultiServer.

How many tools does the TasksMultiServer MCP server expose? +

23 tools across 3 categories: Destructive, Read, Write. 8 are read-only. 15 can modify, create, or delete data.

How do I enforce a policy on TasksMultiServer? +

Register the TasksMultiServer 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 TasksMultiServer tool call.

Deterministic rules across all 23 TasksMultiServer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TASKSMULTISERVER →

Instant setup, no code required.

23 TasksMultiServer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from TasksMultiServer's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →