AdCP — create_media

Create a media buy from selected packages or execute a proposal. Handles validation, approval if needed, and campaign creation. Supports two modes:

Manual Mode: Provide packages array with explicit line item configurations
Proposal Mode: Provide proposal_id and total_budget to execute a proposal from get_products

Response Time: Instant to days (returns completed, working < 120s, or submitted for hours/days) Request Schema: /schemas/3.0.19/media-buy/create-media-buy-request.json Response Schema: /schemas/3.0.19/media-buy/create-media-buy-response.json

Quick Start

Create a simple media buy with two packages:

import { testAgent } from '@adcp/client/testing';
import { CreateMediaBuyResponseSchema } from '@adcp/client';

// Calculate dates dynamically - start tomorrow, end in 90 days
const tomorrow = new Date();
tomorrow.setDate(tomorrow.getDate() + 1);
tomorrow.setHours(0, 0, 0, 0);
const endDate = new Date(tomorrow);
endDate.setDate(endDate.getDate() + 90);

const result = await testAgent.createMediaBuy({
  brand: {
    domain: 'acmecorp.com'
  },
  packages: [
    {
      product_id: 'prod_d979b543',
      pricing_option_id: 'cpm_usd_auction',
      format_ids: [
        {
          agent_url: 'https://creative.adcontextprotocol.org',
          id: 'display_300x250_image'
        }
      ],
      budget: 2500,
      bid_price: 5.00
    },
    {
      product_id: 'prod_e8fd6012',
      pricing_option_id: 'cpm_usd_auction',
      format_ids: [
        {
          agent_url: 'https://creative.adcontextprotocol.org',
          id: 'display_300x250_html'
        }
      ],
      budget: 2500,
      bid_price: 4.50
    }
  ],
  start_time: tomorrow.toISOString(),
  end_time: endDate.toISOString()
});

if (!result.success) {
  throw new Error(`Request failed: ${result.error}`);
}

// Validate response against schema
const validated = CreateMediaBuyResponseSchema.parse(result.data);

// Check for errors (discriminated union response)
if ('errors' in validated && validated.errors) {
  throw new Error(`Failed to create media buy: ${JSON.stringify(validated.errors)}`);
}

if ('media_buy_id' in validated) {
  console.log(`Created media buy ${validated.media_buy_id}`);
  console.log(`Upload creatives by: ${validated.creative_deadline}`);
  console.log(`Packages created: ${validated.packages.length}`);
}

import asyncio
import time
from datetime import datetime, timedelta, timezone
from adcp.testing import test_agent

async def create_campaign():
    # Calculate dates dynamically - start tomorrow, end in 90 days
    tomorrow = datetime.now(timezone.utc).replace(hour=0, minute=0, second=0, microsecond=0) + timedelta(days=1)
    end_date = tomorrow + timedelta(days=90)

    result = await test_agent.simple.create_media_buy(
        brand={
            'domain': 'acmecorp.com'
        },
        packages=[
            {
                'product_id': 'prod_d979b543',
                'pricing_option_id': 'cpm_usd_auction',
                'format_ids': [
                    {
                        'agent_url': 'https://creative.adcontextprotocol.org',
                        'id': 'display_300x250_image'
                    }
                ],
                'budget': 2500,
                'bid_price': 5.00
            },
            {
                'product_id': 'prod_e8fd6012',
                'pricing_option_id': 'cpm_usd_auction',
                'format_ids': [
                    {
                        'agent_url': 'https://creative.adcontextprotocol.org',
                        'id': 'display_300x250_html'
                    }
                ],
                'budget': 2500,
                'bid_price': 4.50
            }
        ],
        start_time=tomorrow.isoformat().replace('+00:00', 'Z'),
        end_time=end_date.isoformat().replace('+00:00', 'Z')
    )

    # Check for errors (discriminated union response)
    if hasattr(result, 'errors') and result.errors:
        raise Exception(f"Failed to create media buy: {result.errors}")

    print(f"Created media buy {result.media_buy_id}")
    print(f"Upload creatives by: {result.creative_deadline}")
    print(f"Packages created: {len(result.packages)}")

asyncio.run(create_campaign())

npx @adcp/client@latest \
  https://test-agent.adcontextprotocol.org/mcp \
  create_media_buy \
  '{"brand":{"domain":"acmecorp.com"},"packages":[{"product_id":"prod_d979b543","pricing_option_id":"cpm_usd_auction","format_ids":[{"agent_url":"https://creative.adcontextprotocol.org","id":"display_300x250_image"}],"budget":30000,"bid_price":5.00},{"product_id":"prod_e8fd6012","pricing_option_id":"cpm_usd_auction","format_ids":[{"agent_url":"https://creative.adcontextprotocol.org","id":"display_300x250_html"}],"budget":20000,"bid_price":4.50}],"start_time":"2025-06-01T00:00:00Z","end_time":"2025-08-31T23:59:59Z"}' \
  --auth $ADCP_AUTH_TOKEN

Request Parameters

Parameter	Type	Required	Description
`account`	account-ref	Yes	Account reference. Pass `{ "account_id": "..." }` or `{ "brand": {...}, "operator": "..." }` if the seller supports implicit resolution. Required for billing and policy evaluation.
`proposal_id`	string	No*	ID of a proposal from `get_products` to execute. Alternative to providing packages.
`total_budget`	TotalBudget	No*	Total budget when executing a proposal. Publisher applies allocation percentages.
`packages`	Package[]	No*	Array of package configurations (see below). Required when not using proposal_id.
`brand`	BrandRef	Yes	Brand reference — resolved to full identity at execution time. See brand.json
`start_time`	string	Yes	`"asap"` or ISO 8601 date-time
`end_time`	string	Yes	ISO 8601 date-time (UTC unless timezone specified)
`invoice_recipient`	BusinessEntity	No	Override the account’s default billing entity for this buy. The seller MUST validate the recipient is authorized and include it in `check_governance` when governance agents are configured.
`po_number`	string	No	Purchase order number
`idempotency_key`	string	No	Unique key for safe retries. If a request with the same key and account has already been processed, the seller returns the existing media buy. MUST be unique per (seller, request) pair. Min 16 chars.
`context`	object	No	Opaque correlation data echoed unchanged in the response. Use for internal tracking, trace IDs, or other caller-specific identifiers.
`reporting_webhook`	ReportingWebhook	No	Automated reporting delivery configuration

* Either packages OR (proposal_id + total_budget) must be provided.

TotalBudget Object

Parameter	Type	Required	Description
`amount`	number	Yes	Total budget amount
`currency`	string	Yes	ISO 4217 currency code

Package Object

Parameter	Type	Required	Description
`product_id`	string	Yes	Product ID from `get_products`
`pricing_option_id`	string	Yes	Pricing option ID from product’s `pricing_options` array
`format_ids`	FormatID[]	Yes	Format IDs that will be used - must be supported by product
`budget`	number	Yes	Budget in currency specified by pricing option
`impressions`	number	No	Impression goal for this package
`paused`	boolean	No	Create package in paused state (default: `false`)
`pacing`	string	No	`"even"` (default), `"asap"`, or `"front_loaded"`
`bid_price`	number	No	Bid price for auction pricing. This is the exact bid/price to honor unless the selected pricing option has `max_bid: true`, in which case it is treated as the buyer’s maximum willingness to pay (ceiling).
`optimization_goals`	OptimizationGoal[]	No	Optimization targets for this package. Each goal is either `kind: "event"` (conversion events with `event_sources` array, optional `cost_per`, `per_ad_spend`, or `maximize_value` target) or `kind: "metric"` (seller-native metric with optional `cost_per` or `threshold_rate` target). Event goals require `conversion_tracking.supported_targets` on the product; metric goals require `metric_optimization.supported_metrics`.
`targeting_overlay`	TargetingOverlay	No	Additional targeting criteria (see Targeting)
`start_time`	string	No	ISO 8601 date-time for this package’s flight start. When omitted, inherits the media buy’s `start_time`. Must fall within the media buy’s date range. Does not support `"asap"`.
`end_time`	string	No	ISO 8601 date-time for this package’s flight end. When omitted, inherits the media buy’s `end_time`. Must fall within the media buy’s date range.
`creative_assignments`	CreativeAssignment[]	No	Assign existing library creatives with optional weights and placement targeting
`creatives`	CreativeAsset[]	No	Upload new creative assets and assign (`creative_id` must not already exist in library)
`context`	object	No	Opaque correlation data echoed unchanged in the package response. Use to map seller-assigned `package_id` back to your internal line items, campaign structure, or tracking state.
`measurement_terms`	MeasurementTerms	No	Buyer’s proposed billing measurement and makegood terms. Overrides product defaults. Seller accepts (echoed on confirmed package), rejects with `TERMS_REJECTED`, or adjusts. When omitted, product’s `measurement_terms` apply.
`performance_standards`	PerformanceStandard[]	No	Buyer’s proposed performance standards (viewability, IVT, completion rate, brand safety, attention score). Overrides product defaults. Seller accepts, rejects with `TERMS_REJECTED`, or adjusts. When omitted, product’s `performance_standards` apply.

Response

Success Response

Field	Description
`media_buy_id`	Seller’s unique identifier
`confirmed_at`	ISO 8601 timestamp of order confirmation. A successful response constitutes confirmation.
`creative_deadline`	ISO 8601 timestamp for creative upload deadline
`packages`	Array of created packages with complete state. Packages may include per-package `creative_deadline` when different from the media buy deadline.

Error Response

Field	Description
`errors`	Array of error objects explaining failure

Submitted Response

Returned when the buy cannot be confirmed synchronously — e.g., guaranteed buys awaiting IO signing, governance review queued, or batched processing. The completion artifact (delivered via tasks/get or push-notification webhook) carries media_buy_id and packages.

Field	Description
`status`	Literal `"submitted"` — discriminates this shape from the sync success branch, whose `status` carries a `MediaBuyStatus` value (`pending_creatives` / `pending_start` / `active`).
`task_id`	Handle the buyer polls with `tasks/get` or receives on webhook callbacks.
`message`	Optional human-readable explanation (e.g., “Awaiting IO signature from sales team”).
`errors`	Optional advisory warnings (non-blocking). Terminal failures belong in the Error Response.

Note: Responses are mutually exclusive across these three shapes. Dispatch on status first: "submitted" → async envelope, otherwise check errors before accessing success fields.

Common Scenarios

Campaign with Targeting

Add geographic restrictions and frequency capping:

import { testAgent } from '@adcp/client/testing';
import { CreateMediaBuyResponseSchema } from '@adcp/client';

// Calculate end date dynamically - 90 days from now
const endDate = new Date();
endDate.setDate(endDate.getDate() + 90);

const result = await testAgent.createMediaBuy({
  brand: {
    domain: 'acmecorp.com'
  },
  packages: [{
    product_id: 'prod_d979b543',
    pricing_option_id: 'cpm_usd_auction',
    format_ids: [{
      agent_url: 'https://creative.adcontextprotocol.org',
      id: 'display_300x250_image'
    }],
    budget: 2500,
    bid_price: 5.00,
    targeting_overlay: {
      geo_countries: ['US'],
      geo_regions: ['US-CA', 'US-NY'],
      frequency_cap: {
        suppress: { interval: 60, unit: 'minutes' }
      }
    }
  }],
  start_time: 'asap',
  end_time: endDate.toISOString()
});

if (!result.success) {
  throw new Error(`Request failed: ${result.error}`);
}

const validated = CreateMediaBuyResponseSchema.parse(result.data);
if ('errors' in validated && validated.errors) {
  throw new Error(`Creation failed: ${JSON.stringify(validated.errors)}`);
}

if ('media_buy_id' in validated) {
  console.log(`Campaign ${validated.media_buy_id} created with targeting`);
}

import asyncio
import time
from datetime import datetime, timedelta, timezone
from adcp.testing import test_agent

async def create_targeted_campaign():
    # Calculate end date dynamically - 90 days from now
    end_date = datetime.now(timezone.utc) + timedelta(days=90)

    result = await test_agent.simple.create_media_buy(
        brand={
            'domain': 'acmecorp.com'
        },
        packages=[{
            'product_id': 'prod_d979b543',
            'pricing_option_id': 'cpm_usd_auction',
            'format_ids': [{
                'agent_url': 'https://creative.adcontextprotocol.org',
                'id': 'display_300x250_image'
            }],
            'budget': 2500,
            'bid_price': 5.00,
            'targeting_overlay': {
                'geo_countries': ['US'],
                'geo_regions': ['US-CA', 'US-NY'],
                'frequency_cap': {
                    'suppress': {'interval': 60, 'unit': 'minutes'}
                }
            }
        }],
        start_time='asap',
        end_time=end_date.isoformat().replace('+00:00', 'Z')
    )

    if hasattr(result, 'errors') and result.errors:
        raise Exception(f"Creation failed: {result.errors}")

    print(f"Campaign {result.media_buy_id} created with targeting")

asyncio.run(create_targeted_campaign())

Campaign with Conversion Optimization

Set a per_ad_spend target for conversion-optimized delivery. The product must declare support in conversion_tracking.supported_targets, and you must have an event source configured via sync_event_sources:

import { testAgent } from '@adcp/client/testing';
import { CreateMediaBuyResponseSchema } from '@adcp/client';

const endDate = new Date();
endDate.setDate(endDate.getDate() + 90);

const result = await testAgent.createMediaBuy({
  brand: {
    domain: 'acmecorp.com'
  },
  packages: [{
    product_id: 'prod_retail_sp',
    pricing_option_id: 'cpc_usd_auction',
    budget: 10000,
    bid_price: 1.20,
    optimization_goals: [{
      kind: 'event',
      event_sources: [
        { event_source_id: 'retailer_sales', event_type: 'purchase', value_field: 'value' }
      ],
      target: { kind: 'per_ad_spend', value: 4.0 },
      priority: 1
    }]
  }],
  start_time: 'asap',
  end_time: endDate.toISOString()
});

if (!result.success) {
  throw new Error(`Request failed: ${result.error}`);
}

const validated = CreateMediaBuyResponseSchema.parse(result.data);
if ('errors' in validated && validated.errors) {
  throw new Error(`Creation failed: ${JSON.stringify(validated.errors)}`);
}

if ('media_buy_id' in validated) {
  console.log(`Campaign ${validated.media_buy_id} created with per_ad_spend target`);
}

import asyncio
import time
from datetime import datetime, timedelta, timezone
from adcp.testing import test_agent

async def create_optimized_campaign():
    end_date = datetime.now(timezone.utc) + timedelta(days=90)

    result = await test_agent.simple.create_media_buy(
        brand={
            'domain': 'acmecorp.com'
        },
        packages=[{
            'product_id': 'prod_retail_sp',
            'pricing_option_id': 'cpc_usd_auction',
            'budget': 10000,
            'bid_price': 1.20,
            'optimization_goals': [{
                'kind': 'event',
                'event_sources': [
                    { 'event_source_id': 'retailer_sales', 'event_type': 'purchase', 'value_field': 'value' }
                ],
                'target': { 'kind': 'per_ad_spend', 'value': 4.0 },
                'priority': 1
            }]
        }],
        start_time='asap',
        end_time=end_date.isoformat().replace('+00:00', 'Z')
    )

    if hasattr(result, 'errors') and result.errors:
        raise Exception(f"Creation failed: {result.errors}")

    print(f"Campaign {result.media_buy_id} created with per_ad_spend target")

asyncio.run(create_optimized_campaign())

Catalog-driven packages

A catalog-driven package allocates a single budget envelope to an entire catalog of items. Instead of creating separate packages per item, the platform optimizes delivery across all catalog items based on performance. This is the AdCP equivalent of catalog-based campaign types such as Google Performance Max or Meta Dynamic Product Ads. Include the catalogs field in a package to make it catalog-driven. Each catalog should have a distinct type (e.g., one product catalog, one store catalog). The referenced catalogs must already be synced via sync_catalogs. Job campaign with synced job catalog:

test=false

{
  "brand": { "domain": "acme-restaurants.com" },
  "packages": [{
    "product_id": "prod_job_board",
    "pricing_option_id": "cpc_eur_auction",
    "budget": 5000,
    "bid_price": 2.50,
    "catalogs": [{
      "catalog_id": "chef-vacancies",
      "type": "job"
    }]
  }],
  "start_time": "asap",
  "end_time": "2026-06-30T23:59:59Z"
}

Retail media with product catalog and store catchment targeting:

test=false

{
  "brand": { "domain": "acmecorp.com" },
  "packages": [{
    "product_id": "prod_retail_sp",
    "pricing_option_id": "cpc_usd_auction",
    "budget": 10000,
    "bid_price": 1.20,
    "catalogs": [{
      "catalog_id": "gmc-primary",
      "type": "product",
      "tags": ["summer"]
    }],
    "targeting_overlay": {
      "store_catchments": [{
        "catalog_id": "retail-locations",
        "catchment_ids": ["drive"]
      }]
    }
  }],
  "start_time": "asap",
  "end_time": "2026-09-30T23:59:59Z"
}

The platform distributes budget across catalog items based on performance. For per-item reporting, use get_media_buy_delivery which returns by_catalog_item breakdowns. Creative variants for catalog-driven packages represent individual catalog items rendered as ads.

Campaign with Inline Creatives

Upload creatives at the same time as creating the campaign:

import { testAgent } from '@adcp/client/testing';
import { CreateMediaBuyResponseSchema } from '@adcp/client';

// Calculate end date dynamically - 90 days from now
const endDate = new Date();
endDate.setDate(endDate.getDate() + 90);

const result = await testAgent.createMediaBuy({
  brand: {
    domain: 'acmecorp.com'
  },
  packages: [{
    product_id: 'prod_d979b543',
    pricing_option_id: 'cpm_usd_auction',
    format_ids: [{
      agent_url: 'https://creative.adcontextprotocol.org',
      id: 'display_300x250_image'
    }],
    budget: 2500,
    bid_price: 5.00,
    creatives: [{
      creative_id: 'hero_video_30s',
      name: 'Hero Video',
      format_id: {
        agent_url: 'https://creative.adcontextprotocol.org',
        id: 'display_300x250_image'
      },
      assets: {
        image: {
          url: 'https://cdn.example.com/hero-banner.jpg',
          width: 300,
          height: 250
        }
      }
    }]
  }],
  start_time: 'asap',
  end_time: endDate.toISOString()
});

if (!result.success) {
  throw new Error(`Request failed: ${result.error}`);
}

const validated = CreateMediaBuyResponseSchema.parse(result.data);
if ('errors' in validated && validated.errors) {
  throw new Error(`Creation failed: ${JSON.stringify(validated.errors)}`);
}

if ('packages' in validated) {
  console.log(`Campaign created with ${validated.packages[0].creative_assignments.length} creatives`);
}

import asyncio
import time
from datetime import datetime, timedelta, timezone
from adcp.testing import test_agent

async def create_with_creatives():
    # Calculate end date dynamically - 90 days from now
    end_date = datetime.now(timezone.utc) + timedelta(days=90)

    result = await test_agent.simple.create_media_buy(
        brand={
            'domain': 'acmecorp.com'
        },
        packages=[{
            'product_id': 'prod_d979b543',
            'pricing_option_id': 'cpm_usd_auction',
            'format_ids': [{
                'agent_url': 'https://creative.adcontextprotocol.org',
                'id': 'display_300x250_image'
            }],
            'budget': 2500,
            'bid_price': 5.00,
            'creatives': [{
                'creative_id': 'hero_video_30s',
                'name': 'Hero Video',
                'format_id': {
                    'agent_url': 'https://creative.adcontextprotocol.org',
                    'id': 'display_300x250_image'
                },
                'assets': {
                    'image': {
                        'url': 'https://cdn.example.com/hero-banner.jpg',
                        'width': 300,
                        'height': 250
                    }
                }
            }]
        }],
        start_time='asap',
        end_time=end_date.isoformat().replace('+00:00', 'Z')
    )

    if hasattr(result, 'errors') and result.errors:
        raise Exception(f"Creation failed: {result.errors}")

    print(f"Campaign created with {len(result.packages[0].creative_assignments)} creatives")

asyncio.run(create_with_creatives())

Campaign with Reporting Webhook

Receive automated reporting notifications:

import { testAgent } from '@adcp/client/testing';
import { CreateMediaBuyResponseSchema } from '@adcp/client';

// Calculate end date dynamically - 90 days from now
const endDate = new Date();
endDate.setDate(endDate.getDate() + 90);

const result = await testAgent.createMediaBuy({
  brand: {
    domain: 'acmecorp.com'
  },
  packages: [{
    product_id: 'prod_d979b543',
    pricing_option_id: 'cpm_usd_auction',
    format_ids: [{
      agent_url: 'https://creative.adcontextprotocol.org',
      id: 'display_300x250_image'
    }],
    budget: 2500,
    bid_price: 5.00
  }],
  start_time: 'asap',
  end_time: endDate.toISOString(),
  reporting_webhook: {
    url: 'https://buyer.example.com/webhooks/reporting',
    authentication: {
      schemes: ['Bearer'],
      credentials: 'secret_token_xyz_minimum_32_chars'
    },
    reporting_frequency: 'daily',
    requested_metrics: ['impressions', 'spend', 'video_completions']
  }
});

if (!result.success) {
  throw new Error(`Request failed: ${result.error}`);
}

const validated = CreateMediaBuyResponseSchema.parse(result.data);
if ('errors' in validated && validated.errors) {
  throw new Error(`Creation failed: ${JSON.stringify(validated.errors)}`);
}

if ('media_buy_id' in validated) {
  console.log(`Campaign created - daily reports will be sent to webhook`);
}

import asyncio
import time
from datetime import datetime, timedelta, timezone
from adcp.testing import test_agent

async def create_with_reporting():
    # Calculate end date dynamically - 90 days from now
    end_date = datetime.now(timezone.utc) + timedelta(days=90)

    result = await test_agent.simple.create_media_buy(
        brand={
            'domain': 'acmecorp.com'
        },
        packages=[{
            'product_id': 'prod_d979b543',
            'pricing_option_id': 'cpm_usd_auction',
            'format_ids': [{
                'agent_url': 'https://creative.adcontextprotocol.org',
                'id': 'display_300x250_image'
            }],
            'budget': 2500,
            'bid_price': 5.00
        }],
        start_time='asap',
        end_time=end_date.isoformat().replace('+00:00', 'Z'),
        reporting_webhook={
            'url': 'https://buyer.example.com/webhooks/reporting',
            'authentication': {
                'schemes': ['Bearer'],
                'credentials': 'secret_token_xyz_minimum_32_chars'
            },
            'reporting_frequency': 'daily',
            'requested_metrics': ['impressions', 'spend', 'video_completions']
        }
    )

    if hasattr(result, 'errors') and result.errors:
        raise Exception(f"Creation failed: {result.errors}")

    print('Campaign created - daily reports will be sent to webhook')

asyncio.run(create_with_reporting())

Executing a Proposal

Execute a proposal from get_products without manually constructing packages:

import { testAgent } from '@adcp/client/testing';
import { CreateMediaBuyResponseSchema } from '@adcp/client';

// Calculate end date dynamically - 90 days from now
const endDate = new Date();
endDate.setDate(endDate.getDate() + 90);

const result = await testAgent.createMediaBuy({
  proposal_id: 'swiss_balanced_v1',  // From get_products response
  total_budget: {
    amount: 50000,
    currency: 'USD'
  },
  brand: {
    domain: 'acmecorp.com'
  },
  start_time: 'asap',
  end_time: endDate.toISOString()
});

if (!result.success) {
  throw new Error(`Request failed: ${result.error}`);
}

const validated = CreateMediaBuyResponseSchema.parse(result.data);
if ('errors' in validated && validated.errors) {
  throw new Error(`Creation failed: ${JSON.stringify(validated.errors)}`);
}

if ('media_buy_id' in validated) {
  // Publisher converted proposal allocations to packages
  console.log(`Created media buy ${validated.media_buy_id}`);
  console.log(`Packages created: ${validated.packages.length}`);
}

import asyncio
import time
from datetime import datetime, timedelta, timezone
from adcp.testing import test_agent

async def execute_proposal():
    # Calculate end date dynamically - 90 days from now
    end_date = datetime.now(timezone.utc) + timedelta(days=90)

    result = await test_agent.simple.create_media_buy(
        proposal_id='swiss_balanced_v1',  # From get_products response
        total_budget={
            'amount': 50000,
            'currency': 'USD'
        },
        brand={
            'domain': 'acmecorp.com'
        },
        start_time='asap',
        end_time=end_date.isoformat().replace('+00:00', 'Z')
    )

    if hasattr(result, 'errors') and result.errors:
        raise Exception(f"Creation failed: {result.errors}")

    # Publisher converted proposal allocations to packages
    print(f"Created media buy {result.media_buy_id}")
    print(f"Packages created: {len(result.packages)}")

asyncio.run(execute_proposal())

When executing a proposal:

The publisher converts allocation percentages to actual budgets using total_budget
Packages are created automatically based on the proposal’s allocations
All other fields (brand, start_time, end_time, etc.) work the same as manual mode

See Proposals for the complete workflow.

Context for Correlation

The context field is an opaque object that sellers echo unchanged in responses and webhooks. Use it to map seller-assigned IDs back to your internal systems without needing to maintain a separate lookup table. Context works at two levels:

Media buy level — echoed in the create_media_buy response
Package level — echoed in each package’s response, useful for mapping package_id back to your internal line items

Mapping to internal campaign and line item IDs:

test=false

{
  "brand": { "domain": "acmecorp.com" },
  "context": {
    "campaign_id": "camp-2026-q3-awareness",
    "planner": "media-team-west",
    "trace_id": "req-8f3a-4b2c"
  },
  "packages": [
    {
      "product_id": "prod_d979b543",
      "pricing_option_id": "cpm_usd_auction",
      "budget": 15000,
      "bid_price": 5.00,
      "context": {
        "line_item_id": "li-001",
        "flight": "june-awareness"
      }
    },
    {
      "product_id": "prod_e8fd6012",
      "pricing_option_id": "cpm_usd_auction",
      "budget": 10000,
      "bid_price": 4.50,
      "context": {
        "line_item_id": "li-002",
        "flight": "june-retargeting"
      }
    }
  ],
  "start_time": "2026-06-01T00:00:00Z",
  "end_time": "2026-08-31T23:59:59Z"
}

The seller’s response echoes your context back alongside the seller-assigned IDs:

test=false

{
  "media_buy_id": "mb_12345",
  "context": {
    "campaign_id": "camp-2026-q3-awareness",
    "planner": "media-team-west",
    "trace_id": "req-8f3a-4b2c"
  },
  "packages": [
    {
      "package_id": "pkg_001",
      "product_id": "prod_d979b543",
      "context": {
        "line_item_id": "li-001",
        "flight": "june-awareness"
      }
    },
    {
      "package_id": "pkg_002",
      "product_id": "prod_e8fd6012",
      "context": {
        "line_item_id": "li-002",
        "flight": "june-retargeting"
      }
    }
  ]
}

Sellers must never parse or act on context data — it exists purely for the buyer’s internal use.

Error Handling

Common errors and resolutions:

Error Code	Description	Resolution
`PRODUCT_NOT_FOUND`	Invalid product_id	Verify product exists via `get_products`
`FORMAT_INCOMPATIBLE`	Format not supported by product	Check product’s `format_ids` field
`BUDGET_TOO_LOW`	Budget below product minimum	Increase budget or choose different product
`TARGETING_TOO_NARROW`	Targeting yields zero inventory	Broaden geographic or audience criteria
`POLICY_VIOLATION`	Brand/product violates policy	Review publisher’s content policies
`INVALID_PRICING_OPTION`	pricing_option_id not found	Use ID from product’s `pricing_options`
`CREATIVE_ID_EXISTS`	Creative ID already exists in library	Use a different `creative_id`, assign existing creatives via `creative_assignments`, or update via `sync_creatives`

Example error response:

{
  "errors": [{
    "code": "FORMAT_INCOMPATIBLE",
    "message": "Product 'prod_d979b543' does not support format 'display_728x90'",
    "field": "packages[0].format_ids",
    "suggestion": "Use display_300x250_image, display_300x250_html, or display_300x250_generative formats"
  }]
}

Key Concepts

Format Specification

Format IDs are required for each package because:

Publishers create placeholder creatives in ad servers
Both parties know exactly what creative assets are needed
Validation ensures products support requested formats
Progress tracking shows which assets are missing

See Format Workflow below for complete details.

Brand reference

The brand field identifies the advertiser for policy compliance and business purposes.

{
  "brand": {
    "domain": "acmecorp.com"
  }
}

Full brand identity data (colors, fonts, product catalog) is resolved from brand.json at execution time. See brand.json.

Pricing & Currency

Each package specifies its pricing_option_id, which determines:

Currency (USD, EUR, etc.)
Pricing model (CPM, CPCV, CPP, etc.)
Rate and whether it’s fixed or auction-based

Packages can use different currencies when sellers support it. See Pricing Models.

Targeting Overlays

Use sparingly - most targeting should be in your brief and handled through product selection. Use overlays only for:

Geographic restrictions (RCT testing, regulatory compliance)
Frequency capping
AXE segment inclusion/exclusion (legacy — new integrations use TMP)

See Targeting for details.

Format Workflow

Why Format Specification Matters

When creating a media buy, format specification enables:

Placeholder Creation - Publisher creates placeholders in ad server with correct specs
Validation - System validates products support requested formats
Clear Expectations - Both parties know exactly what’s needed
Progress Tracking - Track which assets are missing vs. required
Technical Setup - Ad server configured before creatives arrive

Complete Workflow

list_creative_formats → Get available format specifications
get_products → Find products (returns format_ids they support)
Validate compatibility → Ensure products support desired formats
create_media_buy → Specify formats (REQUIRED)
   └── Publisher creates placeholders
   └── Clear creative requirements established
sync_creatives → Upload actual files matching formats
Campaign activation → Replace placeholders with real creatives

Format Validation

Publishers MUST validate:

All formats are supported by the product
Format specifications match list_creative_formats output
Creative requirements can be fulfilled within timeline

Invalid format example:

{
  "errors": [{
    "code": "FORMAT_INCOMPATIBLE",
    "message": "Product 'ctv_sports_premium' does not support format 'audio_standard_30s'",
    "field": "packages[0].format_ids",
    "supported_formats": [
      { "agent_url": "https://creative.adcontextprotocol.org", "id": "video_standard_30s" },
      { "agent_url": "https://creative.adcontextprotocol.org", "id": "video_standard_15s" }
    ]
  }]
}

Flight date validation

When a package specifies start_time or end_time, sellers SHOULD validate that:

Both dates fall within the media buy’s date range
start_time is before end_time

Out-of-range or inverted dates SHOULD return an INVALID_REQUEST error:

{
  "errors": [{
    "code": "INVALID_REQUEST",
    "message": "Package 'week_5' end_time 2026-04-05T23:59:59Z is after media buy end_time 2026-03-31T23:59:59Z",
    "field": "packages[3].end_time"
  }]
}

Asynchronous Operations

This task can complete instantly or take days depending on complexity and approval requirements. The response includes a status field that tells you what happened and what to do next.

Status	Meaning	Your Action
`completed`	Done immediately	Process the result
`working`	Processing (~2 min)	Poll frequently or wait for webhook
`submitted`	Long-running (hours/days)	Use webhooks or poll infrequently
`input-required`	Needs your input	Read message, respond with info
`failed`	Error occurred	Handle the error

Note: For the complete status list see Task Lifecycle.

Immediate Success (`completed`)

The task completed synchronously. No async handling needed.Request:

test=false

const response = await session.call('create_media_buy', {
  brand: { domain: 'acmecorp.com' },
  packages: [
    {
      product_id: 'prod_ctv_sports',
      pricing_option_id: 'cpm_fixed',
      budget: 50000
    }
  ]
});

Response:

{
  "status": "completed",
  "media_buy_id": "mb_12345",
  "confirmed_at": "2025-06-01T10:00:00Z",
  "creative_deadline": "2025-06-15T23:59:59Z",
  "revision": 1,
  "packages": [
    {
      "package_id": "pkg_001",
      "product_id": "prod_ctv_sports"
    }
  ]
}

Long-Running (`submitted`)

The task is queued for manual approval. Configure a webhook to receive updates.Request with webhook:

test=false

const response = await session.call('create_media_buy',
  {
    brand: { domain: 'acmecorp.com' },
    packages: [
      {
        product_id: 'prod_premium_ctv',
        pricing_option_id: 'cpm_fixed',
        budget: 500000  // Large budget triggers approval
      }
    ]
  },
  {
    pushNotificationConfig: {
      url: 'https://your-app.com/webhooks/adcp',
      authentication: {
        schemes: ['bearer'],
        credentials: 'your_webhook_secret'
      }
    }
  }
);

Initial response:

{
  "status": "submitted",
  "task_id": "task_abc123",
  "message": "Budget exceeds auto-approval limit. Sales review required (2-4 hours)."
}

Webhook POST when approved:

{
  "task_id": "task_abc123",
  "task_type": "create_media_buy",
  "status": "completed",
  "timestamp": "2025-01-22T14:30:00Z",
  "message": "Media buy approved and created",
  "result": {
    "media_buy_id": "mb_67890",
    "confirmed_at": "2025-01-22T14:30:00Z",
    "creative_deadline": "2025-06-20T23:59:59Z",
    "revision": 1,
    "packages": [
      {
        "package_id": "pkg_002",
      }
    ]
  }
}

Error (`failed`)

Response:

{
  "status": "failed",
  "errors": [
    {
      "code": "INSUFFICIENT_INVENTORY",
      "message": "Requested targeting yields no available impressions",
      "field": "packages[0].targeting",
      "suggestion": "Expand geographic targeting or increase CPM bid"
    }
  ]
}

Immediate Success (`completed`)

Request:

test=false

const response = await a2a.send({
  message: {
    parts: [{
      kind: 'data',
      data: {
        skill: 'create_media_buy',
        parameters: {
          brand: { domain: 'acmecorp.com' },
          packages: [
            {
              product_id: 'prod_ctv_sports',
              pricing_option_id: 'cpm_fixed',
              budget: 50000
            }
          ]
        }
      }
    }]
  }
});

Response:

{
  "status": "completed",
  "taskId": "task_123",
  "contextId": "ctx_456",
  "artifacts": [{
    "parts": [
      { "text": "Media buy created successfully" },
      {
        "data": {
          "media_buy_id": "mb_12345",
          "confirmed_at": "2025-06-01T10:00:00Z",
          "creative_deadline": "2025-06-15T23:59:59Z",
          "revision": 1,
          "packages": [
            {
              "package_id": "pkg_001",
            }
          ]
        }
      }
    ]
  }]
}

Processing (`working`)

Task is actively processing. Use SSE streaming or poll for updates.Initial response:

{
  "status": "working",
  "taskId": "task_789",
  "contextId": "ctx_456"
}

SSE status update:

{
  "taskId": "task_789",
  "status": {
    "state": "working",
    "message": {
      "parts": [
        { "text": "Validating inventory availability..." },
        {
          "data": {
            "percentage": 50,
            "current_step": "inventory_check"
          }
        }
      ]
    }
  }
}

Long-Running (`submitted`)

Request with push notification:

test=false

const response = await a2a.send({
  message: {
    parts: [{
      kind: 'data',
      data: {
        skill: 'create_media_buy',
        parameters: {
          packages: [{ budget: 500000 }]  // Triggers approval
        }
      }
    }]
  },
  pushNotificationConfig: {
    url: 'https://your-app.com/webhooks/a2a',
    authentication: {
      schemes: ['bearer'],
      credentials: 'your_webhook_secret'
    }
  }
});

Initial response:

{
  "status": "submitted",
  "taskId": "task_abc",
  "contextId": "ctx_456"
}

Webhook POST (Task) when completed:

{
  "id": "task_abc",
  "contextId": "ctx_456",
  "status": {
    "state": "completed",
    "message": {
      "parts": [
        { "text": "Media buy approved and created" },
        {
          "data": {
            "media_buy_id": "mb_67890",
            "packages": [{ "package_id": "pkg_002" }]
          }
        }
      ]
    },
    "timestamp": "2025-01-22T14:30:00Z"
  }
}

Input Required (`input-required`)

Task is paused waiting for clarification or approval.Response:

{
  "status": "input-required",
  "taskId": "task_def",
  "contextId": "ctx_456",
  "artifacts": [{
    "parts": [
      { "text": "The requested budget exceeds your pre-approved limit. Please confirm you want to proceed with $500K spend." },
      {
        "data": {
          "reason": "APPROVAL_REQUIRED",
          "errors": [
            {
              "code": "BUDGET_EXCEEDS_LIMIT",
              "message": "Requested budget exceeds pre-approved limit",
              "field": "total_budget"
            }
          ]
        }
      }
    ]
  }]
}

Follow-up to approve:

test=false

await a2a.send({
  contextId: 'ctx_456',  // Continue the conversation
  message: {
    parts: [{ kind: 'text', text: 'Yes, I confirm the $500K budget' }]
  }
});

Error (`failed`)

Response:

{
  "status": "failed",
  "taskId": "task_xyz",
  "artifacts": [{
    "parts": [
      { "text": "Failed to create media buy" },
      {
        "data": {
          "errors": [
            {
              "code": "INSUFFICIENT_INVENTORY",
              "message": "Requested targeting yields no available impressions",
              "suggestion": "Expand geographic targeting"
            }
          ]
        }
      }
    ]
  }]
}

For complete async handling patterns, see Async Operations.

Usage Notes

Total budget is distributed across packages based on individual budget values
Creative assets must be uploaded before deadline for campaign activation
Impression-time targeting (audience, frequency, suitability) is handled by TMP
Pending states (working, submitted) are normal, not errors
Orchestrators MUST handle pending states as part of normal workflow
Inline creatives: The creatives array creates NEW creatives only. To update existing creatives, use sync_creatives. To assign existing library creatives, use creative_assignments instead.
Inline creative lifecycle: Inline creatives enter the library with the same lifecycle as sync_creatives uploads. If the create_media_buy task resolves as pending_manual and the buy never activates, or if the buy is rejected or canceled, only the package assignments are released — the creatives remain in the library and can be reused by creative_id on a later create_media_buy call. Creative review is independent of the buy outcome; sellers MUST NOT skip review solely because the buy did not activate. Retention of unassigned creatives is seller-defined in 3.0. See Inline creatives on the package.

Content Standards

When a media buy includes content standards (via the governance.content_standards field on get_products responses or the media buy request), the buyer is requesting brand suitability enforcement during delivery.

Content standards are created by calling create_content_standards on a verification agent (e.g., IAS, DoubleVerify). Standards MUST be calibrated with each seller before use in production to ensure the seller’s local evaluation model aligns with the verification agent’s interpretation. See the Content Standards overview for the full setup workflow: create → calibrate → activate → validate.

Policy Compliance

Brand and products are validated during creation. Policy violations return errors:

{
  "errors": [{
    "code": "POLICY_VIOLATION",
    "message": "Brand or product category not permitted on this publisher",
    "field": "brand",
    "suggestion": "Contact publisher for category approval process"
  }]
}

Publishers should ensure:

Brand/products align with selected packages
Creatives match declared brand/products
Campaign complies with all advertising policies

Next Steps

After creating a media buy:

Upload Creatives: Use sync_creatives before deadline
Monitor Status: Use get_media_buy_delivery
Optimize: Use provide_performance_feedback
Update: Use update_media_buy to modify campaign

Learn More

Media Buy Lifecycle - Complete campaign workflow
get_products - Discover inventory
Targeting - Targeting strategies
Pricing Models - Currency and pricing

​Quick Start

​Request Parameters

​TotalBudget Object

​Package Object

​Response

​Success Response

​Error Response

​Submitted Response

​Common Scenarios

​Campaign with Targeting

​Campaign with Conversion Optimization

​Catalog-driven packages

​Campaign with Inline Creatives

​Campaign with Reporting Webhook

​Executing a Proposal

​Context for Correlation

​Error Handling

​Key Concepts

​Format Specification

​Brand reference

​Pricing & Currency

​Targeting Overlays

​Format Workflow

​Why Format Specification Matters

​Complete Workflow

​Format Validation

​Flight date validation

​Asynchronous Operations

​Immediate Success (completed)

​Long-Running (submitted)

​Error (failed)

​Immediate Success (completed)

​Processing (working)

​Long-Running (submitted)

​Input Required (input-required)

​Error (failed)

​Usage Notes

​Content Standards

​Policy Compliance

​Next Steps

​Learn More

Quick Start

Request Parameters

TotalBudget Object

Package Object

Response

Success Response

Error Response

Submitted Response

Common Scenarios

Campaign with Targeting

Campaign with Conversion Optimization

Catalog-driven packages

Campaign with Inline Creatives

Campaign with Reporting Webhook

Executing a Proposal

Context for Correlation

Error Handling

Key Concepts

Format Specification

Brand reference

Pricing & Currency

Targeting Overlays

Format Workflow

Why Format Specification Matters

Complete Workflow

Format Validation

Flight date validation

Asynchronous Operations

Immediate Success (`completed`)

Long-Running (`submitted`)

Error (`failed`)

Immediate Success (`completed`)

Processing (`working`)

Long-Running (`submitted`)

Input Required (`input-required`)

Error (`failed`)

Usage Notes

Content Standards

Policy Compliance

Next Steps

Learn More