meta-ads-mcp 0.7.10__tar.gz → 0.8.0__tar.gz

{meta_ads_mcp-0.7.10 → meta_ads_mcp-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: meta-ads-mcp
-Version: 0.7.10
+Version: 0.8.0
 Summary: Model Context Protocol (MCP) plugin for interacting with Meta Ads API
 Project-URL: Homepage, https://github.com/pipeboard-co/meta-ads-mcp
 Project-URL: Bug Tracker, https://github.com/pipeboard-co/meta-ads-mcp/issues
@@ -111,9 +111,11 @@ For detailed step-by-step instructions, authentication setup, debugging, and tro
 - **Automated Monitoring**: Ask any MCP-compatible LLM to track performance metrics and alert you about significant changes
 - **Budget Optimization**: Get recommendations for reallocating budget to better-performing ad sets
 - **Creative Improvement**: Receive feedback on ad copy, imagery, and calls-to-action
+- **Dynamic Creative Testing**: Easy API for both simple ads (single headline/description) and advanced A/B testing (multiple headlines/descriptions)
 - **Campaign Management**: Request changes to campaigns, ad sets, and ads (all changes require explicit confirmation)
 - **Cross-Platform Integration**: Works with Facebook, Instagram, and all Meta ad platforms
 - **Universal LLM Support**: Compatible with any MCP client including Claude Desktop, Cursor, Cherry Studio, and more
+- **Enhanced Search**: Generic search function includes page searching when queries mention "page" or "pages"
 - **Simple Authentication**: Easy setup with secure OAuth authentication
 - **Cross-Platform Support**: Works on Windows, macOS, and Linux
 
@@ -260,14 +262,32 @@ For local installation configuration, authentication options, and advanced techn
       - `page_id`: Facebook Page ID for the ad
       - `link_url`: Destination URL
       - `message`: Ad copy/text
-      - `headline`: Ad headline
-      - `description`: Ad description
+      - `headline`: Single headline for simple ads (cannot be used with headlines)
+      - `headlines`: List of headlines for dynamic creative testing (cannot be used with headline)
+      - `description`: Single description for simple ads (cannot be used with descriptions)
+      - `descriptions`: List of descriptions for dynamic creative testing (cannot be used with description)
+      - `dynamic_creative_spec`: Dynamic creative optimization settings
       - `call_to_action_type`: CTA button type (e.g., 'LEARN_MORE')
       - `instagram_actor_id`: Optional Instagram account ID
       - `access_token` (optional): Meta API access token
     - Returns: Confirmation with new creative details
 
-15. `mcp_meta_ads_upload_ad_image`
+15. `mcp_meta_ads_update_ad_creative`
+    - Update an existing ad creative with new content or settings
+    - Inputs:
+      - `creative_id`: Meta Ads creative ID to update
+      - `name`: New creative name
+      - `message`: New ad copy/text
+      - `headline`: Single headline for simple ads (cannot be used with headlines)
+      - `headlines`: New list of headlines for dynamic creative testing (cannot be used with headline)
+      - `description`: Single description for simple ads (cannot be used with descriptions)
+      - `descriptions`: New list of descriptions for dynamic creative testing (cannot be used with description)
+      - `dynamic_creative_spec`: New dynamic creative optimization settings
+      - `call_to_action_type`: New call to action button type
+      - `access_token` (optional): Meta API access token (will use cached token if not provided)
+    - Returns: Confirmation with updated creative details
+
+16. `mcp_meta_ads_upload_ad_image`
     - Upload an image to use in Meta Ads creatives
     - Inputs:
       - `account_id`: Meta Ads account ID (format: act_XXXXXXXXX)
@@ -276,14 +296,14 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token
     - Returns: JSON response with image details including hash
 
-16. `mcp_meta_ads_get_ad_image`
+17. `mcp_meta_ads_get_ad_image`
     - Get, download, and visualize a Meta ad image in one step
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
       - `ad_id`: Meta Ads ad ID
     - Returns: The ad image ready for direct visual analysis
 
-17. `mcp_meta_ads_update_ad`
+18. `mcp_meta_ads_update_ad`
     - Update an ad with new settings
     - Inputs:
       - `ad_id`: Meta Ads ad ID
@@ -292,7 +312,7 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
     - Returns: Confirmation with updated ad details and a confirmation link
 
-18. `mcp_meta_ads_update_adset`
+19. `mcp_meta_ads_update_adset`
     - Update an ad set with new settings including frequency caps
     - Inputs:
       - `adset_id`: Meta Ads ad set ID
@@ -304,7 +324,7 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
     - Returns: Confirmation with updated ad set details and a confirmation link
 
-19. `mcp_meta_ads_get_insights`
+20. `mcp_meta_ads_get_insights`
     - Get performance insights for a campaign, ad set, ad or account
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
@@ -314,13 +334,13 @@ For local installation configuration, authentication options, and advanced techn
       - `level`: Level of aggregation (ad, adset, campaign, account)
     - Returns: Performance metrics for the specified object
 
-20. `mcp_meta_ads_get_login_link`
+21. `mcp_meta_ads_get_login_link`
     - Get a clickable login link for Meta Ads authentication
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
     - Returns: A clickable resource link for Meta authentication
 
-21. `mcp_meta-ads_create_budget_schedule`
+22. `mcp_meta-ads_create_budget_schedule`
     - Create a budget schedule for a Meta Ads campaign.
     - Inputs:
       - `campaign_id`: Meta Ads campaign ID.
@@ -331,7 +351,7 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token.
     - Returns: JSON string with the ID of the created budget schedule or an error message.
 
-22. `mcp_meta_ads_search_interests`
+23. `mcp_meta_ads_search_interests`
     - Search for interest targeting options by keyword
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
@@ -339,7 +359,7 @@ For local installation configuration, authentication options, and advanced techn
       - `limit`: Maximum number of results to return (default: 25)
     - Returns: Interest data with id, name, audience_size, and path fields
 
-23. `mcp_meta_ads_get_interest_suggestions`
+24. `mcp_meta_ads_get_interest_suggestions`
     - Get interest suggestions based on existing interests
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
@@ -379,6 +399,14 @@ For local installation configuration, authentication options, and advanced techn
       - `limit`: Maximum number of results to return (default: 25)
     - Returns: Location data with key, name, type, and geographic hierarchy information
 
+28. `mcp_meta_ads_search` (Enhanced)
+    - Generic search across accounts, campaigns, ads, and pages
+    - Automatically includes page searching when query mentions "page" or "pages"
+    - Inputs:
+      - `access_token` (optional): Meta API access token (will use cached token if not provided)
+      - `query`: Search query string (e.g., "Injury Payouts pages", "active campaigns")
+    - Returns: List of matching record IDs in ChatGPT-compatible format
+
 ## Privacy and Security
 
 Meta Ads MCP follows security best practices with secure token management and automatic authentication handling. 

{meta_ads_mcp-0.7.10 → meta_ads_mcp-0.8.0}/README.md

@@ -86,9 +86,11 @@ For detailed step-by-step instructions, authentication setup, debugging, and tro
 - **Automated Monitoring**: Ask any MCP-compatible LLM to track performance metrics and alert you about significant changes
 - **Budget Optimization**: Get recommendations for reallocating budget to better-performing ad sets
 - **Creative Improvement**: Receive feedback on ad copy, imagery, and calls-to-action
+- **Dynamic Creative Testing**: Easy API for both simple ads (single headline/description) and advanced A/B testing (multiple headlines/descriptions)
 - **Campaign Management**: Request changes to campaigns, ad sets, and ads (all changes require explicit confirmation)
 - **Cross-Platform Integration**: Works with Facebook, Instagram, and all Meta ad platforms
 - **Universal LLM Support**: Compatible with any MCP client including Claude Desktop, Cursor, Cherry Studio, and more
+- **Enhanced Search**: Generic search function includes page searching when queries mention "page" or "pages"
 - **Simple Authentication**: Easy setup with secure OAuth authentication
 - **Cross-Platform Support**: Works on Windows, macOS, and Linux
 
@@ -235,14 +237,32 @@ For local installation configuration, authentication options, and advanced techn
       - `page_id`: Facebook Page ID for the ad
       - `link_url`: Destination URL
       - `message`: Ad copy/text
-      - `headline`: Ad headline
-      - `description`: Ad description
+      - `headline`: Single headline for simple ads (cannot be used with headlines)
+      - `headlines`: List of headlines for dynamic creative testing (cannot be used with headline)
+      - `description`: Single description for simple ads (cannot be used with descriptions)
+      - `descriptions`: List of descriptions for dynamic creative testing (cannot be used with description)
+      - `dynamic_creative_spec`: Dynamic creative optimization settings
       - `call_to_action_type`: CTA button type (e.g., 'LEARN_MORE')
       - `instagram_actor_id`: Optional Instagram account ID
       - `access_token` (optional): Meta API access token
     - Returns: Confirmation with new creative details
 
-15. `mcp_meta_ads_upload_ad_image`
+15. `mcp_meta_ads_update_ad_creative`
+    - Update an existing ad creative with new content or settings
+    - Inputs:
+      - `creative_id`: Meta Ads creative ID to update
+      - `name`: New creative name
+      - `message`: New ad copy/text
+      - `headline`: Single headline for simple ads (cannot be used with headlines)
+      - `headlines`: New list of headlines for dynamic creative testing (cannot be used with headline)
+      - `description`: Single description for simple ads (cannot be used with descriptions)
+      - `descriptions`: New list of descriptions for dynamic creative testing (cannot be used with description)
+      - `dynamic_creative_spec`: New dynamic creative optimization settings
+      - `call_to_action_type`: New call to action button type
+      - `access_token` (optional): Meta API access token (will use cached token if not provided)
+    - Returns: Confirmation with updated creative details
+
+16. `mcp_meta_ads_upload_ad_image`
     - Upload an image to use in Meta Ads creatives
     - Inputs:
       - `account_id`: Meta Ads account ID (format: act_XXXXXXXXX)
@@ -251,14 +271,14 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token
     - Returns: JSON response with image details including hash
 
-16. `mcp_meta_ads_get_ad_image`
+17. `mcp_meta_ads_get_ad_image`
     - Get, download, and visualize a Meta ad image in one step
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
       - `ad_id`: Meta Ads ad ID
     - Returns: The ad image ready for direct visual analysis
 
-17. `mcp_meta_ads_update_ad`
+18. `mcp_meta_ads_update_ad`
     - Update an ad with new settings
     - Inputs:
       - `ad_id`: Meta Ads ad ID
@@ -267,7 +287,7 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
     - Returns: Confirmation with updated ad details and a confirmation link
 
-18. `mcp_meta_ads_update_adset`
+19. `mcp_meta_ads_update_adset`
     - Update an ad set with new settings including frequency caps
     - Inputs:
       - `adset_id`: Meta Ads ad set ID
@@ -279,7 +299,7 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
     - Returns: Confirmation with updated ad set details and a confirmation link
 
-19. `mcp_meta_ads_get_insights`
+20. `mcp_meta_ads_get_insights`
     - Get performance insights for a campaign, ad set, ad or account
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
@@ -289,13 +309,13 @@ For local installation configuration, authentication options, and advanced techn
       - `level`: Level of aggregation (ad, adset, campaign, account)
     - Returns: Performance metrics for the specified object
 
-20. `mcp_meta_ads_get_login_link`
+21. `mcp_meta_ads_get_login_link`
     - Get a clickable login link for Meta Ads authentication
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
     - Returns: A clickable resource link for Meta authentication
 
-21. `mcp_meta-ads_create_budget_schedule`
+22. `mcp_meta-ads_create_budget_schedule`
     - Create a budget schedule for a Meta Ads campaign.
     - Inputs:
       - `campaign_id`: Meta Ads campaign ID.
@@ -306,7 +326,7 @@ For local installation configuration, authentication options, and advanced techn
       - `access_token` (optional): Meta API access token.
     - Returns: JSON string with the ID of the created budget schedule or an error message.
 
-22. `mcp_meta_ads_search_interests`
+23. `mcp_meta_ads_search_interests`
     - Search for interest targeting options by keyword
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
@@ -314,7 +334,7 @@ For local installation configuration, authentication options, and advanced techn
       - `limit`: Maximum number of results to return (default: 25)
     - Returns: Interest data with id, name, audience_size, and path fields
 
-23. `mcp_meta_ads_get_interest_suggestions`
+24. `mcp_meta_ads_get_interest_suggestions`
     - Get interest suggestions based on existing interests
     - Inputs:
       - `access_token` (optional): Meta API access token (will use cached token if not provided)
@@ -354,6 +374,14 @@ For local installation configuration, authentication options, and advanced techn
       - `limit`: Maximum number of results to return (default: 25)
     - Returns: Location data with key, name, type, and geographic hierarchy information
 
+28. `mcp_meta_ads_search` (Enhanced)
+    - Generic search across accounts, campaigns, ads, and pages
+    - Automatically includes page searching when query mentions "page" or "pages"
+    - Inputs:
+      - `access_token` (optional): Meta API access token (will use cached token if not provided)
+      - `query`: Search query string (e.g., "Injury Payouts pages", "active campaigns")
+    - Returns: List of matching record IDs in ChatGPT-compatible format
+
 ## Privacy and Security
 
 Meta Ads MCP follows security best practices with secure token management and automatic authentication handling. 

{meta_ads_mcp-0.7.10 → meta_ads_mcp-0.8.0}/meta_ads_mcp/__init__.py

@@ -7,7 +7,7 @@ with the Claude LLM.
 
 from meta_ads_mcp.core.server import main
 
-__version__ = "0.7.10"
+__version__ = "0.8.0"
 
 __all__ = [
     'get_ad_accounts',

{meta_ads_mcp-0.7.10 → meta_ads_mcp-0.8.0}/meta_ads_mcp/core/ads.py

@@ -633,7 +633,10 @@ async def create_ad_creative(
     link_url: str = None,
     message: str = None,
     headline: str = None,
+    headlines: List[str] = None,
     description: str = None,
+    descriptions: List[str] = None,
+    dynamic_creative_spec: Dict[str, Any] = None,
     call_to_action_type: str = None,
     instagram_actor_id: str = None
 ) -> str:
@@ -648,8 +651,11 @@ async def create_ad_creative(
         page_id: Facebook Page ID to be used for the ad
         link_url: Destination URL for the ad
         message: Ad copy/text
-        headline: Ad headline
-        description: Ad description
+        headline: Single headline for simple ads (cannot be used with headlines)
+        headlines: List of headlines for dynamic creative testing (cannot be used with headline)
+        description: Single description for simple ads (cannot be used with descriptions)
+        descriptions: List of descriptions for dynamic creative testing (cannot be used with description)
+        dynamic_creative_spec: Dynamic creative optimization settings
         call_to_action_type: Call to action button type (e.g., 'LEARN_MORE', 'SIGN_UP', 'SHOP_NOW')
         instagram_actor_id: Optional Instagram account ID for Instagram placements
     
@@ -697,29 +703,98 @@ async def create_ad_creative(
                 "suggestion": "Please provide a page_id parameter or use get_account_pages to find available pages"
             }, indent=2)
     
+    # Validate headline/description parameters - cannot mix simple and complex
+    if headline and headlines:
+        return json.dumps({"error": "Cannot specify both 'headline' and 'headlines'. Use 'headline' for single headline or 'headlines' for multiple."}, indent=2)
+    
+    if description and descriptions:
+        return json.dumps({"error": "Cannot specify both 'description' and 'descriptions'. Use 'description' for single description or 'descriptions' for multiple."}, indent=2)
+    
+    # Convert simple parameters to complex format for internal processing
+    final_headlines = None
+    final_descriptions = None
+    
+    if headline:
+        final_headlines = [headline]
+    elif headlines:
+        final_headlines = headlines
+        
+    if description:
+        final_descriptions = [description]
+    elif descriptions:
+        final_descriptions = descriptions
+    
+    # Validate dynamic creative parameters
+    if final_headlines:
+        if len(final_headlines) > 5:
+            return json.dumps({"error": "Maximum 5 headlines allowed for dynamic creatives"}, indent=2)
+        for i, h in enumerate(final_headlines):
+            if len(h) > 40:
+                return json.dumps({"error": f"Headline {i+1} exceeds 40 character limit"}, indent=2)
+    
+    if final_descriptions:
+        if len(final_descriptions) > 5:
+            return json.dumps({"error": "Maximum 5 descriptions allowed for dynamic creatives"}, indent=2)
+        for i, d in enumerate(final_descriptions):
+            if len(d) > 125:
+                return json.dumps({"error": f"Description {i+1} exceeds 125 character limit"}, indent=2)
+    
     # Prepare the creative data
     creative_data = {
-        "name": name,
-        "object_story_spec": {
+        "name": name
+    }
+    
+    # Choose between asset_feed_spec (dynamic creative) or object_story_spec (traditional)
+    if final_headlines or final_descriptions:
+        # Use asset_feed_spec for dynamic creatives
+        asset_feed_spec = {
+            "ad_formats": ["SINGLE_IMAGE"],
+            "images": [{"hash": image_hash}],
+            "link_urls": [{"website_url": link_url if link_url else "https://facebook.com"}]
+        }
+        
+        # Handle headlines
+        if final_headlines:
+            asset_feed_spec["headlines"] = [{"text": headline_text} for headline_text in final_headlines]
+            
+        # Handle descriptions  
+        if final_descriptions:
+            asset_feed_spec["descriptions"] = [{"text": description_text} for description_text in final_descriptions]
+        
+        # Add message as primary_texts if provided
+        if message:
+            asset_feed_spec["primary_texts"] = [{"text": message}]
+        
+        # Add call_to_action_types if provided
+        if call_to_action_type:
+            asset_feed_spec["call_to_action_types"] = [call_to_action_type]
+        
+        creative_data["asset_feed_spec"] = asset_feed_spec
+        
+        # For dynamic creatives, we need a simplified object_story_spec
+        creative_data["object_story_spec"] = {
+            "page_id": page_id
+        }
+    else:
+        # Use traditional object_story_spec for single creative
+        creative_data["object_story_spec"] = {
             "page_id": page_id,
             "link_data": {
                 "image_hash": image_hash,
                 "link": link_url if link_url else "https://facebook.com"
             }
         }
-    }
-    
-    # Add optional parameters if provided
-    if message:
-        creative_data["object_story_spec"]["link_data"]["message"] = message
-    
-    if headline:
-        creative_data["object_story_spec"]["link_data"]["name"] = headline
         
-    if description:
-        creative_data["object_story_spec"]["link_data"]["description"] = description
+        # Add optional parameters if provided
+        if message:
+            creative_data["object_story_spec"]["link_data"]["message"] = message
     
-    if call_to_action_type:
+    # Add dynamic creative spec if provided
+    if dynamic_creative_spec:
+        creative_data["dynamic_creative_spec"] = dynamic_creative_spec
+    
+    # Only add call_to_action to object_story_spec if we're not using asset_feed_spec
+    if call_to_action_type and "asset_feed_spec" not in creative_data:
         creative_data["object_story_spec"]["link_data"]["call_to_action"] = {
             "type": call_to_action_type
         }
@@ -739,7 +814,7 @@ async def create_ad_creative(
             creative_id = data["id"]
             creative_endpoint = f"{creative_id}"
             creative_params = {
-                "fields": "id,name,status,thumbnail_url,image_url,image_hash,object_story_spec,url_tags,link_url"
+                "fields": "id,name,status,thumbnail_url,image_url,image_hash,object_story_spec,asset_feed_spec,url_tags,link_url"
             }
             
             creative_details = await make_api_request(creative_endpoint, access_token, creative_params)
@@ -759,6 +834,154 @@ async def create_ad_creative(
         }, indent=2)
 
 
+@mcp_server.tool()
+@meta_api_tool
+async def update_ad_creative(
+    access_token: str = None,
+    creative_id: str = None,
+    name: str = None,
+    message: str = None,
+    headline: str = None,
+    headlines: List[str] = None,
+    description: str = None,
+    descriptions: List[str] = None,
+    dynamic_creative_spec: Dict[str, Any] = None,
+    call_to_action_type: str = None
+) -> str:
+    """
+    Update an existing ad creative with new content or settings.
+    
+    Args:
+        access_token: Meta API access token (optional - will use cached token if not provided)
+        creative_id: Meta Ads creative ID to update
+        name: New creative name
+        message: New ad copy/text
+        headline: Single headline for simple ads (cannot be used with headlines)
+        headlines: New list of headlines for dynamic creative testing (cannot be used with headline)
+        description: Single description for simple ads (cannot be used with descriptions)
+        descriptions: New list of descriptions for dynamic creative testing (cannot be used with description)
+        dynamic_creative_spec: New dynamic creative optimization settings
+        call_to_action_type: New call to action button type
+    
+    Returns:
+        JSON response with updated creative details
+    """
+    # Check required parameters
+    if not creative_id:
+        return json.dumps({"error": "No creative ID provided"}, indent=2)
+    
+    # Validate headline/description parameters - cannot mix simple and complex
+    if headline and headlines:
+        return json.dumps({"error": "Cannot specify both 'headline' and 'headlines'. Use 'headline' for single headline or 'headlines' for multiple."}, indent=2)
+    
+    if description and descriptions:
+        return json.dumps({"error": "Cannot specify both 'description' and 'descriptions'. Use 'description' for single description or 'descriptions' for multiple."}, indent=2)
+    
+    # Convert simple parameters to complex format for internal processing
+    final_headlines = None
+    final_descriptions = None
+    
+    if headline:
+        final_headlines = [headline]
+    elif headlines:
+        final_headlines = headlines
+        
+    if description:
+        final_descriptions = [description]
+    elif descriptions:
+        final_descriptions = descriptions
+    
+    # Validate dynamic creative parameters
+    if final_headlines:
+        if len(final_headlines) > 5:
+            return json.dumps({"error": "Maximum 5 headlines allowed for dynamic creatives"}, indent=2)
+        for i, h in enumerate(final_headlines):
+            if len(h) > 40:
+                return json.dumps({"error": f"Headline {i+1} exceeds 40 character limit"}, indent=2)
+    
+    if final_descriptions:
+        if len(final_descriptions) > 5:
+            return json.dumps({"error": "Maximum 5 descriptions allowed for dynamic creatives"}, indent=2)
+        for i, d in enumerate(final_descriptions):
+            if len(d) > 125:
+                return json.dumps({"error": f"Description {i+1} exceeds 125 character limit"}, indent=2)
+    
+    # Prepare the update data
+    update_data = {}
+    
+    if name:
+        update_data["name"] = name
+    
+    if message:
+        update_data["object_story_spec"] = {"link_data": {"message": message}}
+    
+    # Handle dynamic creative assets via asset_feed_spec
+    if final_headlines or final_descriptions or dynamic_creative_spec:
+        asset_feed_spec = {}
+        
+        # Add required ad_formats field for dynamic creatives
+        asset_feed_spec["ad_formats"] = ["SINGLE_IMAGE"]
+        
+        # Handle headlines
+        if final_headlines:
+            asset_feed_spec["headlines"] = [{"text": headline_text} for headline_text in final_headlines]
+            
+        # Handle descriptions  
+        if final_descriptions:
+            asset_feed_spec["descriptions"] = [{"text": description_text} for description_text in final_descriptions]
+        
+        # Add message as primary_texts if provided
+        if message:
+            asset_feed_spec["primary_texts"] = [{"text": message}]
+        
+        update_data["asset_feed_spec"] = asset_feed_spec
+    
+    # Add dynamic creative spec if provided
+    if dynamic_creative_spec:
+        update_data["dynamic_creative_spec"] = dynamic_creative_spec
+    
+    # Handle call_to_action - add to asset_feed_spec if using dynamic creative, otherwise to object_story_spec
+    if call_to_action_type:
+        if "asset_feed_spec" in update_data:
+            update_data["asset_feed_spec"]["call_to_action_types"] = [call_to_action_type]
+        else:
+            if "object_story_spec" not in update_data:
+                update_data["object_story_spec"] = {"link_data": {}}
+            update_data["object_story_spec"]["link_data"]["call_to_action"] = {
+                "type": call_to_action_type
+            }
+    
+    # Prepare the API endpoint for updating the creative
+    endpoint = f"{creative_id}"
+    
+    try:
+        # Make API request to update the creative
+        data = await make_api_request(endpoint, access_token, update_data, method="POST")
+        
+        # If successful, get more details about the updated creative
+        if "id" in data:
+            creative_endpoint = f"{creative_id}"
+            creative_params = {
+                "fields": "id,name,status,thumbnail_url,image_url,image_hash,object_story_spec,url_tags,link_url,dynamic_creative_spec"
+            }
+            
+            creative_details = await make_api_request(creative_endpoint, access_token, creative_params)
+            return json.dumps({
+                "success": True,
+                "creative_id": creative_id,
+                "details": creative_details
+            }, indent=2)
+        
+        return json.dumps(data, indent=2)
+    
+    except Exception as e:
+        return json.dumps({
+            "error": "Failed to update ad creative",
+            "details": str(e),
+            "update_data_sent": update_data
+        }, indent=2)
+
+
 async def _discover_pages_for_account(account_id: str, access_token: str) -> dict:
     """
     Internal function to discover pages for an account using multiple approaches.

{meta_ads_mcp-0.7.10 → meta_ads_mcp-0.8.0}/meta_ads_mcp/core/openai_deep_research.py

@@ -77,6 +77,32 @@ class MetaAdsDataManager:
             logger.error(f"Error fetching ads for {account_id}: {e}")
             return []
     
+    async def _get_pages_for_account(self, access_token: str, account_id: str) -> List[Dict[str, Any]]:
+        """Get pages associated with an account"""
+        try:
+            # Import the page discovery function from ads module
+            from .ads import _discover_pages_for_account
+            
+            # Ensure account_id has the 'act_' prefix
+            if not account_id.startswith("act_"):
+                account_id = f"act_{account_id}"
+            
+            page_discovery_result = await _discover_pages_for_account(account_id, access_token)
+            
+            if not page_discovery_result.get("success"):
+                return []
+            
+            # Return page data in a consistent format
+            return [{
+                "id": page_discovery_result["page_id"],
+                "name": page_discovery_result.get("page_name", "Unknown"),
+                "source": page_discovery_result.get("source", "unknown"),
+                "account_id": account_id
+            }]
+        except Exception as e:
+            logger.error(f"Error fetching pages for {account_id}: {e}")
+            return []
+    
     async def search_records(self, query: str, access_token: str) -> List[str]:
         """Search Meta Ads data and return matching record IDs
         
@@ -176,6 +202,34 @@ class MetaAdsDataManager:
                                 },
                                 "raw_data": ad
                             }
+            
+            # If query specifically mentions "page" or "pages", also search pages
+            if any(term in ['page', 'pages', 'facebook page'] for term in query_terms):
+                for account in accounts[:5]:  # Limit to first 5 accounts for performance
+                    pages = await self._get_pages_for_account(access_token, account['id'])
+                    for page in pages:
+                        page_text = f"{page.get('name', '')} {page.get('source', '')}".lower()
+                        
+                        if any(term in page_text for term in query_terms):
+                            page_record_id = f"page:{page['id']}"
+                            matching_ids.append(page_record_id)
+                            
+                            # Cache the page data
+                            self._cache[page_record_id] = {
+                                "id": page_record_id,
+                                "type": "page",
+                                "title": f"Facebook Page: {page.get('name', 'Unnamed Page')}",
+                                "text": f"Facebook Page {page.get('name', 'Unnamed')} (ID: {page.get('id', 'N/A')}) - Source: {page.get('source', 'Unknown')}, Account: {account.get('name', 'Unknown')}",
+                                "metadata": {
+                                    "page_id": page.get('id'),
+                                    "page_name": page.get('name'),
+                                    "source": page.get('source'),
+                                    "account_id": account.get('id'),
+                                    "account_name": account.get('name'),
+                                    "data_type": "meta_ads_page"
+                                },
+                                "raw_data": page
+                            }
         
         except Exception as e:
             logger.error(f"Error during search operation: {e}")
@@ -219,7 +273,7 @@ async def search(
     Search through Meta Ads data and return matching record IDs.
     
     This tool is required for OpenAI ChatGPT Deep Research integration.
-    It searches across ad accounts, campaigns, and ads to find relevant records
+    It searches across ad accounts, campaigns, ads, and pages to find relevant records
     based on the provided query.
     
     Args:
@@ -233,6 +287,7 @@ async def search(
         search(query="active campaigns")
         search(query="account spending")
         search(query="facebook ads performance")
+        search(query="facebook pages")
     """
     if not query:
         return json.dumps({
@@ -285,6 +340,7 @@ async def fetch(
         fetch(id="account:act_123456789")
         fetch(id="campaign:23842588888640185")
         fetch(id="ad:23842614006130185")
+        fetch(id="page:123456789")
     """
     if not id:
         return json.dumps({