Meta Ads MCP

Instructions

Get interest suggestions based on existing interests.

Args:
    interest_list: List of interest names to get suggestions for (e.g., ["Basketball", "Soccer"])
    access_token: Meta API access token (optional - will use cached token if not provided)  
    limit: Maximum number of suggestions to return (default: 25)

Returns:
    JSON string containing suggested interests with id, name, audience_size, and description fields

Implementation Reference

• meta_ads_mcp/core/targeting.py:39-65 (handler)

  The primary handler function for the 'get_interest_suggestions' tool. It is decorated with @mcp_server.tool() for MCP registration and @meta_api_tool. The function accepts a list of interests, queries Meta's API search endpoint with type='adinterestsuggestion', and returns formatted JSON suggestions.

  @mcp_server.tool()
  @meta_api_tool
  async def get_interest_suggestions(interest_list: List[str], access_token: Optional[str] = None, limit: int = 25) -> str:
      """
      Get interest suggestions based on existing interests.
      
      Args:
          interest_list: List of interest names to get suggestions for (e.g., ["Basketball", "Soccer"])
          access_token: Meta API access token (optional - will use cached token if not provided)  
          limit: Maximum number of suggestions to return (default: 25)
      
      Returns:
          JSON string containing suggested interests with id, name, audience_size, and description fields
      """
      if not interest_list:
          return json.dumps({"error": "No interest list provided"}, indent=2)
      
      endpoint = "search"
      params = {
          "type": "adinterestsuggestion", 
          "interest_list": json.dumps(interest_list),
          "limit": limit
      }
      
      data = await make_api_request(endpoint, access_token, params)
      
      return json.dumps(data, indent=2)

• meta_ads_mcp/core/__init__.py:14-45 (registration)

  Re-export of get_interest_suggestions from targeting.py into the core package namespace via __all__, making it available for MCP server registration.

  from .targeting import search_interests, get_interest_suggestions, estimate_audience_size, search_behaviors, search_demographics, search_geo_locations
  from . import reports  # Import module to register conditional tools
  from . import duplication  # Import module to register conditional duplication tools
  from .openai_deep_research import search, fetch  # OpenAI MCP Deep Research tools
  
  __all__ = [
      'mcp_server',
      'get_ad_accounts',
      'get_account_info',
      'get_campaigns',
      'get_campaign_details',
      'create_campaign',
      'get_adsets',
      'get_adset_details',
      'update_adset',
      'get_ads',
      'get_ad_details',
      'get_ad_creatives',
      'get_ad_image',
      'update_ad',
      'get_insights',
      # Note: 'get_login_link' is registered conditionally by the authentication module
      'login_cli',
      'login',
      'main',
      'create_budget_schedule',
      'search_interests',
      'get_interest_suggestions',
      'estimate_audience_size',
      'search_behaviors',
      'search_demographics',
      'search_geo_locations',

• meta_ads_mcp/__init__.py:30-61 (registration)

  Package-level export and import of get_interest_suggestions in the main __init__.py, exposing the tool at the root package level.

      'get_interest_suggestions',
      'estimate_audience_size',
      'search_behaviors',
      'search_demographics',
      'search_geo_locations'
  ]
  
  # Import key functions to make them available at package level
  from .core import (
      get_ad_accounts,
      get_account_info,
      get_campaigns,
      get_campaign_details,
      create_campaign,
      get_adsets,
      get_adset_details,
      update_adset,
      get_ads,
      get_ad_details,
      get_ad_creatives,
      get_ad_image,
      update_ad,
      get_insights,
      login_cli,
      main,
      search_interests,
      get_interest_suggestions,
      estimate_audience_size,
      search_behaviors,
      search_demographics,
      search_geo_locations
  )