// SCAN REPORT

Pipiads

73 tools. 7 can modify or destroy data without limits.

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

Last updated: 5 Jul 2026

7 can modify or destroy data

66 read-only

73 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 70 of 73 tools

How to control Pipiads ↓

TOOL MAP

What Pipiads exposes to your agents

Read (66) Write / Execute (5) Destructive / Financial (2)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Pipiads costs in tokens

16,167 tokens of tool definitions, loaded on every request

8.1% of a 200k context window

1,051 heaviest tool: search_ads

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Pipiads tools

Destructive · Medium cancel_monitor_task Cancelling a monitoring task is typically irreversible - once cancelled, the task's ongoing monitoring state, collected data, and scheduling are lost. Destructive · High delete_monitor_group This tool permanently removes a monitor group, which is a destructive operation that cannot be undone. Write · Low create_monitor_group This tool creates a new monitoring group configuration. Write · Medium create_monitor_task The tool creates a new resource (a monitoring task) which is a reversible write operation.

7 of Pipiads's 73 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Pipiads

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

Deny destructive operations

{
  "cancel_monitor_task": {
    "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_monitor_group": {
    "limits": [
      {
        "counter": "create_monitor_group_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ai_search_image_ads": {
    "limits": [
      {
        "counter": "ai_search_image_ads_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 Pipiads — 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 PIPIADS →

Instant setup, no code required.

FULL CATALOGUE

All 73 Pipiads tools

DESTRUCTIVE 2 tools

Destructive cancel_monitor_task Cancel an ad monitoring task. Destructive delete_monitor_group Delete a monitor group.

WRITE 5 tools

Write create_monitor_group Create a new monitor task group. Write create_monitor_task Create an ad monitoring task for a Facebook advertiser. Write save_monitor_notifications Save notification settings (email, instant alerts, reports). Write set_monitor_task_group Assign a monitor task to a group. Write update_monitor_group Update a monitor group name.

READ 66 tools

EXPLORE

Related servers

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

FAQ

Questions about Pipiads

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

Yes. The Pipiads server exposes 2 destructive tools including cancel_monitor_task, delete_monitor_group. 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 Pipiads? +

The Pipiads server has 5 write tools including create_monitor_group, create_monitor_task, save_monitor_notifications. 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 Pipiads.

How many tools does the Pipiads MCP server expose? +

73 tools across 3 categories: Destructive, Read, Write. 66 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Pipiads? +

Register the Pipiads 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 Pipiads tool call.

Deterministic rules across all 73 Pipiads tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PIPIADS →

Instant setup, no code required.

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