// SCAN REPORT

AgentCloak

8 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 12 Jun 2026

1 can modify or destroy data

7 read-only

8 tools total

Community server · catalogue entry verified 12/06/2026

How to control AgentCloak ↓

TOOL MAP

What AgentCloak exposes to your agents

Read (7) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous AgentCloak tools

Write · Medium create_draft This tool creates or modifies email drafts, which is a Write operation.

1 of AgentCloak's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AgentCloak

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

Rate limit write operations

{
  "create_draft": {
    "limits": [
      {
        "counter": "create_draft_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_provider_info": {
    "limits": [
      {
        "counter": "get_provider_info_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 AgentCloak — 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 AGENTCLOAK →

Free to start. No card required.

FULL CATALOGUE

All 8 AgentCloak tools

WRITE 1 tools

Write create_draft Create an email draft. The draft is saved but NOT sent. The user must manually review and send it. When replyi

READ 7 tools

Read get_provider_info Get information about the email provider type, supported search operators, and limitations. Call this to under Read get_thread Get all messages in an email thread. Each message is sanitized through the content filter pipeline. Read list_drafts List email drafts. Returns draft metadata including recipients and subjects. Read list_labels List all Gmail labels with unread message counts. Read list_threads List email threads matching a query. Returns thread summaries with participant lists. For broad queries, use a Read read_email Read the full content of an email by message ID. Content is sanitized and filtered for safety. Read search_emails Search emails by query. Returns sanitized email summaries with sensitive content filtered. For broad queries (

FAQ

Questions about AgentCloak

How do I prevent bulk modifications through AgentCloak? +

The AgentCloak server has 1 write tools including create_draft. 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 AgentCloak.

How many tools does the AgentCloak MCP server expose? +

8 tools across 2 categories: Read, Write. 7 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on AgentCloak? +

Register the AgentCloak 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 AgentCloak tool call.

Deterministic rules across all 8 AgentCloak tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENTCLOAK →

Free to start. No card required.

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