Protocol Comparison

Compare MCP and A2A protocols for AdCP integration. Both use the same unified status system with different transport formats.

Both MCP and A2A provide identical AdCP capabilities using the same unified status system. They differ only in transport format and async handling.

Quick Comparison

Aspect	MCP	A2A
Request Style	Tool calls	Task messages
Response Style	Direct JSON	Artifacts
Status System	Unified status field	Unified status field
Async Handling	Polling with tasks/get	SSE streaming
Webhooks	Protocol wrapper extension	Native PushNotificationConfig
Task Management	tasks/list, tasks/get tools	Native tasks/list, tasks/get
Context	Manual (pass context_id)	Automatic (protocol-managed)
Best For	Claude, AI assistants	Agent workflows

Unified Status System

Both protocols use the same status field with consistent values.

Status Handling (Both Protocols)

Every response includes a status field that tells you exactly what to do:

{
  "status": "input-required",    // Same values for both protocols
  "message": "Need your budget", // Same human explanation
  // ... protocol-specific formatting below
}

Status	What It Means	Your Action
completed	Task finished	Process data, show success
input-required	Need user input	Read message, prompt user, follow up
working	Processing (< 120s)	Poll frequently, show progress
submitted	Long-running (hours to days)	Provide webhook or poll less frequently
failed	Error occurred	Show error, handle gracefully
auth-required	Need auth	Prompt for credentials

See Task Lifecycle for complete status handling guide.

Transport Format Differences

Same status and data, different packaging:

MCP Response Format

{
  "status": "input-required",
  "message": "I need your budget and target audience",
  "context_id": "ctx-123",
  "products": [],
  "suggestions": ["budget", "audience"]
}

A2A Response Format

{
  "status": "input-required",
  "contextId": "ctx-123",
  "artifacts": [{
    "artifactId": "artifact-product-discovery-xyz",
    "name": "product_discovery",
    "parts": [
      {
        "kind": "text",
        "text": "I need your budget and target audience"
      },
      {
        "kind": "data",
        "data": {
          "products": [],
          "suggestions": ["budget", "audience"]
        }
      }
    ]
  }]
}

Async Operation Differences

Both protocols handle async operations with the same status progression: submitted → working → completed/failed

MCP Async Pattern

// Initial response with task_id
{
  "status": "submitted",
  "message": "Creating media buy, requires manual approval",
  "context_id": "ctx-123",
  "task_id": "task-456",
}

// Poll using tasks/get
const updates = await session.call('tasks/get', {
  task_id: "task-456",
  include_result: true
});

// Optional: Configure webhook
const response = await session.call('create_media_buy', params, {
  push_notification_config: {
    url: "https://buyer.com/webhooks",
    authentication: {
      schemes: ["HMAC-SHA256"],
      credentials: "shared_secret_32_chars"
    }
  }
});

A2A Async Pattern

// Initial response with native task tracking
{
  "status": "submitted",
  "taskId": "task-456",
  "contextId": "ctx-123",
  "estimatedCompletionTime": "2025-01-23T10:00:00Z"
}

// Real-time updates via SSE
const events = new EventSource(`/tasks/${response.taskId}/events`);
events.onmessage = (event) => {
  const update = JSON.parse(event.data);
  console.log(`Status: ${update.status}, Message: ${update.message}`);
};

// Native webhook support
await a2a.send({
  message: { /* skill invocation */ },
  push_notification_config: {
    webhook_url: "https://buyer.com/webhooks",
    authentication: {
      schemes: ["Bearer"],
      credentials: "secret_token_min_32_chars"
    }
  }
});

Context Management

MCP: Manual Context

let contextId = null;

async function callAdcp(request) {
  if (contextId) {
    request.context_id = contextId;
  }

  const response = await mcp.call('get_products', request);
  contextId = response.context_id; // Save for next call

  return response;
}

A2A: Automatic Context

// A2A manages context automatically
const response1 = await a2a.send({ message: "Find video products" });
const response2 = await a2a.send({
  contextId: response1.contextId, // Optional - A2A tracks this
  message: "Focus on premium inventory"
});

Clarification Handling

Both protocols use the same status: "input-required" pattern:

// Works for both MCP and A2A
function handleResponse(response) {
  if (response.status === 'input-required') {
    const info = promptUser(response.message);
    return sendFollowUp(response.context_id, info);
  }

  if (response.status === 'completed') {
    return processResults(response);
  }
}

Error Handling

Both use status: "failed" with same error structure:

{
  "status": "failed",
  "message": "Insufficient inventory for your targeting criteria",
  "context_id": "ctx-123",
  "error_code": "insufficient_inventory",
  "suggestions": ["Expand targeting", "Increase CPM"]
}

Choosing a Protocol

Choose MCP if you’re using:

• Claude Desktop or Claude Code
• MCP-compatible AI assistants
• Simple tool-based integrations
• Direct JSON responses

Choose A2A if you’re using:

• Google AI agents or Agent Engine
• Multi-modal workflows (text + files)
• Real-time streaming updates
• Artifact-based data handling

Both protocols provide:

• Same AdCP tasks and capabilities
• Unified status system for clear client logic
• Context management for conversations
• Async operation support
• Human-in-the-loop workflows
• Error handling and recovery

Next Steps

• MCP Guide: See MCP Guide for tool calls and context management
• A2A Guide: See A2A Guide for artifacts and streaming
• Both protocols: Provide the same capabilities with unified status handling