Meta

30 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
30 read-only
30 tools total

Community server · catalogue entry verified 30/06/2026

How to control Meta ↓

What Meta exposes to your agents

Read (30) Write / Execute (0) Destructive / Financial (0)

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

How to control Meta

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

Cap read operations
{
  "ad_account_get": {
    "limits": [
      {
        "counter": "ad_account_get_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Meta — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON META →

Instant setup, no code required.

All 30 Meta tools

READ 30 tools
Read ad_account_get GET /act_{id}. Read ad_accounts_list GET /me/adaccounts. Read adcreative_get GET /{creative_id}. Read adcreatives_list GET /act_{id}/adcreatives. Read ads_list GET /{parent}/ads. Read adsets_list GET /{parent}/adsets. Read campaign_get GET /{campaign_id}. Read campaigns_list GET /act_{id}/campaigns. Read debug_token GET /debug_token — returns token type (USER / PAGE / APP / SYSTEM_USER), app_id, expires_at, scopes, is_valid. Read graph_get Escape-hatch: raw GET to any Graph API endpoint. Path must start with Read ig_business_account_get GET /{ig_user_id}. Note: ig_user_id is NOT the @username — it Read ig_hashtag_media GET /{hashtag_id}/top_media or /{hashtag_id}/recent_media. user_id is required by Meta. Read ig_hashtag_search GET /ig_hashtag_search?q=...&user_id=... — returns the hashtag id used by ig_hashtag_media. Read ig_media_get GET /{media_id}. Read ig_media_insights GET /{media_id}/insights. Metric set depends on media_type: Read ig_media_list GET /{ig_user_id}/media. Read ig_user_insights GET /{ig_user_id}/insights. Period is required. Read insights GET /{object_id}/insights. Sync only — for huge date ranges Meta recommends async jobs (POST /insights → polli Read page_get GET /{page_id} — page metadata. Read page_insights GET /{page_id}/insights. Requires a Page Access Token (resolved automatically). Read page_posts Default edge is Read pages_list GET /me/accounts — returns pages with id, name and (importantly) access_token for each. Read post_comments GET /{post_id}/comments. Read post_get GET /{post_id}. Post id format is usually Read wa_analytics GET /{waba_id}?fields=analytics.start({start}).end({end}).granularity({granularity}) — Read wa_business_owned_wabas GET /{business_id}/owned_whatsapp_business_accounts — returns WABAs owned by the parent Business. Read wa_message_templates GET /{waba_id}/message_templates. Read wa_phone_number_get GET /{phone_number_id} — includes quality_rating, messaging_limit_tier, name_status, verified_name. Read wa_phone_numbers GET /{waba_id}/phone_numbers. Read wa_template_get GET /{template_id}.

Related servers

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

Questions about Meta

Is the Meta MCP server safe to use without restrictions? +

The Meta server is primarily read-only with 30 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Meta MCP server expose? +

30 tools across 3 categories: Execute, Read, Write. 30 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Meta? +

Register the Meta 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 Meta tool call.

Deterministic rules across all 30 Meta tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.