Skip to main content
Glama

create_campaign

Create new Meta advertising campaigns with outcome-based objectives, budget controls, and bid strategies to manage Facebook and Instagram ads.

Instructions

Create a new campaign in a Meta Ads account.

Args:
    account_id: Meta Ads account ID (format: act_XXXXXXXXX)
    name: Campaign name
    objective: Campaign objective (ODAX, outcome-based). Must be one of:
               OUTCOME_AWARENESS, OUTCOME_TRAFFIC, OUTCOME_ENGAGEMENT,
               OUTCOME_LEADS, OUTCOME_SALES, OUTCOME_APP_PROMOTION.
               Note: Legacy objectives like BRAND_AWARENESS, LINK_CLICKS,
               CONVERSIONS, APP_INSTALLS, etc. are not valid for new
               campaigns and will cause a 400 error. Use the outcome-based
               values above (e.g., BRAND_AWARENESS → OUTCOME_AWARENESS).
    access_token: Meta API access token (optional - will use cached token if not provided)
    status: Initial campaign status (default: PAUSED)
    special_ad_categories: List of special ad categories if applicable
    daily_budget: Daily budget in account currency (in cents) as a string (only used if use_adset_level_budgets=False)
    lifetime_budget: Lifetime budget in account currency (in cents) as a string (only used if use_adset_level_budgets=False)
    buying_type: Buying type (e.g., 'AUCTION')
    bid_strategy: Bid strategy. Must be one of: 'LOWEST_COST_WITHOUT_CAP', 'LOWEST_COST_WITH_BID_CAP', 'COST_CAP', 'LOWEST_COST_WITH_MIN_ROAS'.
    bid_cap: Bid cap in account currency (in cents) as a string
    spend_cap: Spending limit for the campaign in account currency (in cents) as a string
    campaign_budget_optimization: Whether to enable campaign budget optimization (only used if use_adset_level_budgets=False)
    ab_test_control_setups: Settings for A/B testing (e.g., [{"name":"Creative A", "ad_format":"SINGLE_IMAGE"}])
    use_adset_level_budgets: If True, budgets will be set at the ad set level instead of campaign level (default: False)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
account_idYes
nameYes
objectiveYes
access_tokenNo
statusNoPAUSED
special_ad_categoriesNo
daily_budgetNo
lifetime_budgetNo
buying_typeNo
bid_strategyNo
bid_capNo
spend_capNo
campaign_budget_optimizationNo
ab_test_control_setupsNo
use_adset_level_budgetsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The primary handler for the 'create_campaign' tool. This function defines the tool's parameters with type annotations and docstring describing inputs/outputs, validates inputs, constructs API parameters (handling budgets, special categories as JSON, etc.), and performs a POST request to the Meta Ads API endpoint /{account_id}/campaigns using make_api_request. Decorators @mcp_server.tool() and @meta_api_tool register it as an MCP tool.
    @mcp_server.tool()
    @meta_api_tool
    async def create_campaign(
        account_id: str,
        name: str,
        objective: str,
        access_token: Optional[str] = None,
        status: str = "PAUSED",
        special_ad_categories: Optional[List[str]] = None,
        daily_budget: Optional[int] = None,
        lifetime_budget: Optional[int] = None,
        buying_type: Optional[str] = None,
        bid_strategy: Optional[str] = None,
        bid_cap: Optional[int] = None,
        spend_cap: Optional[int] = None,
        campaign_budget_optimization: Optional[bool] = None,
        ab_test_control_setups: Optional[List[Dict[str, Any]]] = None,
        use_adset_level_budgets: bool = False
    ) -> str:
        """
        Create a new campaign in a Meta Ads account.
        
        Args:
            account_id: Meta Ads account ID (format: act_XXXXXXXXX)
            name: Campaign name
            objective: Campaign objective (ODAX, outcome-based). Must be one of:
                       OUTCOME_AWARENESS, OUTCOME_TRAFFIC, OUTCOME_ENGAGEMENT,
                       OUTCOME_LEADS, OUTCOME_SALES, OUTCOME_APP_PROMOTION.
                       Note: Legacy objectives like BRAND_AWARENESS, LINK_CLICKS,
                       CONVERSIONS, APP_INSTALLS, etc. are not valid for new
                       campaigns and will cause a 400 error. Use the outcome-based
                       values above (e.g., BRAND_AWARENESS → OUTCOME_AWARENESS).
            access_token: Meta API access token (optional - will use cached token if not provided)
            status: Initial campaign status (default: PAUSED)
            special_ad_categories: List of special ad categories if applicable
            daily_budget: Daily budget in account currency (in cents) as a string (only used if use_adset_level_budgets=False)
            lifetime_budget: Lifetime budget in account currency (in cents) as a string (only used if use_adset_level_budgets=False)
            buying_type: Buying type (e.g., 'AUCTION')
            bid_strategy: Bid strategy. Must be one of: 'LOWEST_COST_WITHOUT_CAP', 'LOWEST_COST_WITH_BID_CAP', 'COST_CAP', 'LOWEST_COST_WITH_MIN_ROAS'.
            bid_cap: Bid cap in account currency (in cents) as a string
            spend_cap: Spending limit for the campaign in account currency (in cents) as a string
            campaign_budget_optimization: Whether to enable campaign budget optimization (only used if use_adset_level_budgets=False)
            ab_test_control_setups: Settings for A/B testing (e.g., [{"name":"Creative A", "ad_format":"SINGLE_IMAGE"}])
            use_adset_level_budgets: If True, budgets will be set at the ad set level instead of campaign level (default: False)
        """
        # Check required parameters
        if not account_id:
            return json.dumps({"error": "No account ID provided"}, indent=2)
        
        if not name:
            return json.dumps({"error": "No campaign name provided"}, indent=2)
            
        if not objective:
            return json.dumps({"error": "No campaign objective provided"}, indent=2)
        
        # Special_ad_categories is required by the API, set default if not provided
        if special_ad_categories is None:
            special_ad_categories = []
        
        # For this example, we'll add a fixed daily budget if none is provided and we're not using ad set level budgets
        if not daily_budget and not lifetime_budget and not use_adset_level_budgets:
            daily_budget = "1000"  # Default to $10 USD
        
        endpoint = f"{account_id}/campaigns"
        
        params = {
            "name": name,
            "objective": objective,
            "status": status,
            "special_ad_categories": json.dumps(special_ad_categories)  # Properly format as JSON string
        }
        
        # Only set campaign-level budgets if we're not using ad set level budgets
        if not use_adset_level_budgets:
            # Convert budget values to strings if they aren't already
            if daily_budget is not None:
                params["daily_budget"] = str(daily_budget)
            
            if lifetime_budget is not None:
                params["lifetime_budget"] = str(lifetime_budget)
            
            if campaign_budget_optimization is not None:
                params["campaign_budget_optimization"] = "true" if campaign_budget_optimization else "false"
        
        # Add new parameters
        if buying_type:
            params["buying_type"] = buying_type
        
        if bid_strategy:
            params["bid_strategy"] = bid_strategy
        
        if bid_cap is not None:
            params["bid_cap"] = str(bid_cap)
        
        if spend_cap is not None:
            params["spend_cap"] = str(spend_cap)
        
        if ab_test_control_setups:
            params["ab_test_control_setups"] = json.dumps(ab_test_control_setups)
        
        try:
            data = await make_api_request(endpoint, access_token, params, method="POST")
            
            # Add a note about budget strategy if using ad set level budgets
            if use_adset_level_budgets:
                data["budget_strategy"] = "ad_set_level"
                data["note"] = "Campaign created with ad set level budgets. Set budgets when creating ad sets within this campaign."
            
            return json.dumps(data, indent=2)
        except Exception as e:
            error_msg = str(e)
            return json.dumps({
                "error": "Failed to create campaign",
                "details": error_msg,
                "params_sent": params
            }, indent=2)
  • Registers 'create_campaign' by importing it from campaigns.py into the core package namespace, allowing it to be used and further exported.
    from .campaigns import get_campaigns, get_campaign_details, create_campaign
  • Re-exports 'create_campaign' from core package into the top-level meta_ads_mcp package namespace via import, making it available for use.
    create_campaign,
  • Includes 'create_campaign' in core.__all__, explicitly registering it for import from the core package (from meta_ads_mcp.core import create_campaign).
    'create_campaign',
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden and does well by disclosing critical behavioral traits: it warns about 400 errors for legacy objectives, explains default values (status: PAUSED), clarifies budget usage conditions, and mentions optional token caching. However, it doesn't cover rate limits, authentication requirements beyond token, or error handling details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized for a complex 15-parameter tool and front-loaded with the core purpose. The parameter explanations are necessary but somewhat dense; some formatting (like the objective list) could be more structured. Every sentence adds value, though the Args: section is lengthy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the high complexity (15 parameters, no annotations) but presence of an output schema, the description is quite complete: it covers all parameters thoroughly, explains behavioral constraints, and provides implementation guidance. The output schema likely handles return values, so the description appropriately focuses on input semantics and usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by providing detailed semantic information for all 15 parameters: it explains formats (e.g., 'act_XXXXXXXXX'), enumerates valid values for objective, clarifies dependencies (e.g., budget parameters only used if use_adset_level_budgets=False), and provides examples for complex parameters like ab_test_control_setups.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Create a new campaign') and resource ('in a Meta Ads account'), distinguishing it from sibling tools like update_campaign or get_campaigns. The verb+resource combination is precise and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context through parameter explanations (e.g., legacy objectives cause errors) but doesn't explicitly state when to use this tool versus alternatives like update_campaign or create_adset. No explicit when-not or alternative guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pipeboard-co/meta-ads-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server