// SCAN REPORT

Zeph To

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

8 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

8 can modify or destroy data

2 read-only

10 tools total

Community server · catalogue entry verified 03/07/2026

How to control Zeph To ↓

TOOL MAP

What Zeph To exposes to your agents

Read (2) Write / Execute (8) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Zeph To tools

Write · Low zeph_dismiss This tool marks a notification as read/dismissed, which is a reversible state change (the notification data still exists, just marked as read). Write · Medium zeph_broadcast This tool sends notifications to users, which is a reversible write operation (notifications can be dismissed or archived). Write · Low zeph_clipboard Copying text to clipboard is a Write operation: it modifies system state (clipboard contents) reversibly and without side effects beyond the immediate clipboard modification. Write · Medium zeph_dismiss_all This tool modifies data by clearing notifications from a notification feed.

8 of Zeph To's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Zeph To

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

Rate limit write operations

{
  "zeph_broadcast": {
    "limits": [
      {
        "counter": "zeph_broadcast_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "zeph_ask": {
    "limits": [
      {
        "counter": "zeph_ask_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 Zeph To — 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 ZEPH TO →

Instant setup, no code required.

FULL CATALOGUE

All 10 Zeph To tools

WRITE 8 tools

Write zeph_broadcast Send a push notification to all subscribers of a channel. Use zeph://channels resource to find available chann Write zeph_clipboard Copy text to the user\ Write zeph_dismiss Dismiss (mark as read) a specific push notification by ID. Use after processing a notification to clear it fro Write zeph_dismiss_all Dismiss all push notifications at once. Clears the entire notification feed. Write zeph_file Send a text file to the user\ Write zeph_input Request text input from the user via push notification. The tool blocks until the user responds or the timeout Write zeph_notify Send a one-way push notification to the user\ Write zeph_prompt Ask the user to choose from predefined options via push notification. The tool blocks until the user responds

READ 2 tools

Read zeph_ask Ask the user a question with optional quick-reply buttons and a text input field. Combines prompt (buttons) an Read zeph_list List recent push notifications. Use this to check notification history, avoid duplicates, or reference previou

EXPLORE

Related servers

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

FAQ

Questions about Zeph To

How do I prevent bulk modifications through Zeph To? +

The Zeph To server has 8 write tools including zeph_broadcast, zeph_clipboard, zeph_dismiss. 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 Zeph To.

How many tools does the Zeph To MCP server expose? +

10 tools across 3 categories: Destructive, Read, Write. 2 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Zeph To? +

Register the Zeph To 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 Zeph To tool call.

Deterministic rules across all 10 Zeph To tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ZEPH TO →

Instant setup, no code required.

10 Zeph To tools catalogued and risk-classified — across an index of 43,000+ MCP servers.