// SCAN REPORT

Manus MCP

3 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

3 can modify or destroy data

0 read-only

3 tools total

Community server · catalogue entry verified 29/06/2026

How to control Manus MCP ↓

TOOL MAP

What Manus MCP exposes to your agents

Read (0) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Manus MCP tools

Destructive · High delete_webhook This tool permanently removes a webhook, which cannot be undone without recreating it. Write · Medium create_task This tool creates new data (an AI task) in the Manus system. Write · Medium create_webhook This tool creates/registers a new webhook resource, which is a reversible state modification.

3 of Manus MCP's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Manus MCP

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

Deny destructive operations

{
  "delete_webhook": {
    "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

{
  "create_task": {
    "limits": [
      {
        "counter": "create_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Create a free account and register Manus MCP — 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 MANUS →

Instant setup, no code required.

FULL CATALOGUE

All 3 Manus MCP tools

DESTRUCTIVE 1 tools

Destructive delete_webhook Remove a previously registered webhook by its ID.

WRITE 2 tools

Write create_task Create a new AI task in Manus. Returns task_id, task_title, task_url, and optionally a shareable link. Write create_webhook Register a new webhook to receive real-time notifications from Manus. Returns webhook details.

EXPLORE

Related servers

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

FAQ

Questions about Manus MCP

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

Yes. The Manus MCP server exposes 1 destructive tools including delete_webhook. 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 Manus MCP? +

The Manus MCP server has 2 write tools including create_task, create_webhook. 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 Manus MCP.

How many tools does the Manus MCP server expose? +

3 tools across 2 categories: Destructive, Write. 0 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Manus MCP? +

Register the Manus 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 Manus MCP tool call.

Deterministic rules across all 3 Manus MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MANUS →

Instant setup, no code required.

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