// SCAN REPORT

Agent1st Ads

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

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

Last updated: 29 Jun 2026

7 can modify or destroy data

8 read-only

15 tools total

Community server · catalogue entry verified 29/06/2026

How to control Agent1st Ads ↓

TOOL MAP

What Agent1st Ads exposes to your agents

Read (8) Write / Execute (2) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Agent1st Ads tools

Financial · Critical create_tiktok_campaign This tool creates an ad campaign that commits real financial spend (minimum $20/day budget). Financial · High enable_meta_campaign Enabling a Meta campaign directly causes real money to be spent on advertising. Financial · High update_meta_campaign_budget Modifying an ad campaign's daily budget directly controls how much money is spent on advertising. Financial · High update_tiktok_campaign_budget Modifying ad campaign budgets directly controls financial spend commitments.

7 of Agent1st Ads's 15 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Agent1st Ads

PolicyLayer is an MCP gateway — it sits between your AI agents and Agent1st Ads, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "create_tiktok_campaign": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations

{
  "delete_meta_campaign": {
    "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_meta_campaign": {
    "limits": [
      {
        "counter": "create_meta_campaign_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_setup": {
    "limits": [
      {
        "counter": "check_setup_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 Agent1st Ads — 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 AGENT1ST ADS →

Instant setup, no code required.

FULL CATALOGUE

All 15 Agent1st Ads tools

FINANCIAL 4 tools

Financial create_tiktok_campaign Create a complete TikTok ad campaign in one call — campaign + ad group with targeting + ad. Created in DISABLE Financial enable_meta_campaign Activate a paused Meta campaign so it starts spending. Use campaign_id from create_meta_campaign or list_meta_ Financial update_meta_campaign_budget Change the daily budget of a Meta campaign. Takes effect immediately. Increase to scale a winning campaign, de Financial update_tiktok_campaign_budget Change the daily budget of a TikTok campaign. TikTok minimum is $20/day. Requires Pro plan or higher ($69/mo).

DESTRUCTIVE 1 tools

Destructive delete_meta_campaign Permanently delete a Meta campaign and all its ad sets and ads. Cannot be undone. Use pause_meta_campaign to s

EXECUTE 1 tools

Execute enable_tiktok_campaign Activate a disabled TikTok campaign so it starts running. Requires Pro plan or higher ($69/mo).

WRITE 1 tools

Write create_meta_campaign Create a complete Meta (Facebook/Instagram) ad campaign in one call — campaign + ad set with targeting + creat

READ 8 tools

Read check_setup ALWAYS call this first. Verifies license tier and which ad platforms are connected. Shows what is available ba Read get_ad_account_info Get current balance, total spend, currency, and account status for all connected ad accounts (Meta and/or TikT Read get_meta_campaign_stats Get performance metrics for a Meta campaign: impressions, clicks, spend (USD), CTR, CPM, and conversions. Use Read get_tiktok_campaign_stats Get performance metrics for a TikTok campaign: impressions, clicks, spend, CTR, CPC, conversions. Requires Pro Read list_meta_campaigns List all campaigns in the Meta (Facebook/Instagram) ad account with campaign ID, name, status (ACTIVE/PAUSED/A Read list_tiktok_campaigns List all campaigns in the TikTok ad account with campaign ID, name, status, objective, and budget. Requires Pr Read pause_meta_campaign Pause a live Meta campaign to stop all spending immediately. Campaign and settings are preserved — use enable_ Read pause_tiktok_campaign Pause a running TikTok campaign to stop all spending. Settings preserved — use enable_tiktok_campaign to resum

EXPLORE

Related servers

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

FAQ

Questions about Agent1st Ads

Can an AI agent move money through the Agent1st Ads MCP server? +

Yes. The Agent1st Ads server exposes 4 financial tools including create_tiktok_campaign, enable_meta_campaign, update_meta_campaign_budget. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the Agent1st Ads MCP server? +

Yes. The Agent1st Ads server exposes 1 destructive tools including delete_meta_campaign. 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 Agent1st Ads? +

The Agent1st Ads server has 1 write tools including create_meta_campaign. 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 Agent1st Ads.

How many tools does the Agent1st Ads MCP server expose? +

15 tools across 3 categories: Destructive, Read, Write. 8 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Agent1st Ads? +

Register the Agent1st Ads 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 Agent1st Ads tool call.

Deterministic rules across all 15 Agent1st Ads tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENT1ST ADS →

Instant setup, no code required.

15 Agent1st Ads tools catalogued and risk-classified — across an index of 43,000+ MCP servers.