> ## Documentation Index > Fetch the complete documentation index at: https://docs.adcontextprotocol.org/llms.txt > Use this file to discover all available pages before exploring further. # A2B: Testing your first agent call > Module A2B: Hands-on lab — initialize an MCP session, call get_products, place a media buy, attach creatives, and handle real response shapes with copy-paste curl examples. # A2B: Testing your first agent call **Free module** — No account required. \~20 minutes with Addie. Prerequisite: [A2](/docs/learning/foundations/a2-protocol-architecture). ## Learning objectives * Initialize a stateful MCP session against the AdCP test agent * Call `get_products` with a natural-language brief and read the product response * Place a media buy with `create_media_buy` and handle all three response shapes * Attach creatives with `sync_creatives` and check buy status via `get_media_buys` * Diagnose and resolve auth failures, schema mismatches, and async polling delays ## Reading list End-to-end buyer workflow from setup to delivery. Media buy status states — pending\_creatives, pending\_start, active, paused, completed — and what each means for the buyer. Full field reference, required fields, and all three response shapes. How to attach assets to a buy, dry-run validation, and assignment patterns. Error codes, retry behavior, and how to read the `errors[]` array. Session initialization, the `mcp-session-id` header, and tool call format. ## Test agent All curl examples below target the AdCP training agent: ``` https://test-agent.adcontextprotocol.org/mcp ``` You'll need an API key from your [AgenticAdvertising.org dashboard](https://agenticadvertising.org/dashboard). Replace `` in every example. ## What you'll do with Addie Walk through five calls in sequence. Addie demonstrates each call, shows the raw response, then guides you through reproducing it yourself. 1. **Initialize** — open a stateful MCP session; save the `mcp-session-id` header 2. **Discover** — `get_products` with a brief; read proposals 3. **Buy** — `create_media_buy`; handle all three response shapes 4. **Attach creatives** — `sync_creatives`; validate with dry-run first 5. **Poll status** — `get_media_buys` until `valid_actions` shows the buy is serving ## Step-by-step curl reference Use these as a quick reference while working through the module with Addie, or to reproduce any step independently. ### Step 1 — Initialize a session Every sequence starts with an `initialize` call. The response sets the protocol version and returns an `mcp-session-id` header — save it. ```bash theme={null} curl -X POST https://test-agent.adcontextprotocol.org/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -d '{ "jsonrpc": "2.0", "method": "initialize", "params": { "protocolVersion": "2024-11-05", "capabilities": {}, "clientInfo": { "name": "my-buyer-agent", "version": "1.0" } }, "id": 1 }' ``` The response includes an `mcp-session-id` in the response headers. Every subsequent call must include it: ``` mcp-session-id: ``` ### Step 2 — Discover products Call `get_products` with `buying_mode: "brief"` and a plain-English description of your campaign goals. The agent returns curated `products[]` and ready-to-execute `proposals[]`. ```bash theme={null} curl -X POST https://test-agent.adcontextprotocol.org/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -H "mcp-session-id: " \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "get_products", "arguments": { "adcp_major_version": 3, "buying_mode": "brief", "brief": "CTV campaign, adults 25-54 in the US, $50K budget, brand safety required" } }, "id": 2 }' ``` The result is in `content[0].text` as JSON. Look for `proposals[0].proposal_id` — you'll pass it to `create_media_buy`. ### Step 3 — Place a media buy Pass the `proposal_id` from Step 2 and a `total_budget`. The `idempotency_key` lets you safely retry if the network drops — use a fresh UUID v4 per request. ```bash theme={null} curl -X POST https://test-agent.adcontextprotocol.org/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -H "mcp-session-id: " \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "create_media_buy", "arguments": { "adcp_major_version": 3, "idempotency_key": "mb-lab-20260428-001", "account": { "brand": { "domain": "nova-motors.com" }, "operator": "pinnacle-media.com" }, "proposal_id": "", "total_budget": { "amount": 50000, "currency": "USD" } } }, "id": 3 }' ``` **Three response shapes — you'll see one of these:** | Shape | What it means | Next step | | -------------------------------------------------------- | -------------------------------- | ----------------------------------------------------------------------------- | | `media_buy_id` + `status: "pending_creatives"` | Buy confirmed; attach creatives | Go to Step 4 | | `media_buy_id` + `status: "pending_start"` or `"active"` | Buy confirmed and ready | Creatives already attached or not required | | `status: "submitted"` + `task_id` | Buy queued for async processing | Poll the AdCP task with `task_id` (see [Async polling](#async-polling) below) | | `errors[]` present, no `media_buy_id` | Rejected — read `errors[0].code` | Fix the request and retry with a new `idempotency_key` | ### Step 4 — Attach creatives A buy in `pending_creatives` state can't serve until you call `sync_creatives`. Use `dry_run: true` first to validate your creative shapes without writing anything. ```bash theme={null} curl -X POST https://test-agent.adcontextprotocol.org/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -H "mcp-session-id: " \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "sync_creatives", "arguments": { "adcp_major_version": 3, "idempotency_key": "sc-lab-20260428-001", "account": { "brand": { "domain": "nova-motors.com" }, "operator": "pinnacle-media.com" }, "creatives": [ { "creative_id": "nova-ctv-30s-v1", "format_id": { "agent_url": "https://test-agent.adcontextprotocol.org", "id": "ctv_1920x1080_30s" }, "assets": [ { "asset_id": "video_url", "url": "https://cdn.example.com/nova-ctv-30s.mp4" } ] } ], "dry_run": true } }, "id": 4 }' ``` Remove `"dry_run": true` to apply. The response includes `creatives[].status` — `approved`, `pending_review`, or `rejected`. ### Step 5 — Check status Poll `get_media_buys` with the `media_buy_id` from Step 3 to see lifecycle state and `valid_actions`. ```bash theme={null} curl -X POST https://test-agent.adcontextprotocol.org/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -H "mcp-session-id: " \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "get_media_buys", "arguments": { "adcp_major_version": 3, "media_buy_ids": [""] } }, "id": 5 }' ``` The `media_buys[0].status` field is one of `pending_creatives`, `pending_start`, `active`, `paused`, `completed`, `rejected`, or `canceled`. The `valid_actions` array tells you what the buyer can do next. ## Async polling When `create_media_buy` returns `status: "submitted"` and a `task_id`, the buy is queued. Poll until the task completes: ```bash theme={null} curl -X POST https://test-agent.adcontextprotocol.org/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer " \ -H "mcp-session-id: " \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "get_task_status", "arguments": { "task_id": "", "include_result": true } }, "id": 6 }' ``` `get_task_status` is an AdCP application-layer task polling tool. In 3.x, sellers that do not advertise this alias still expose the legacy AdCP `tasks/get` surface with the same snake\_case payload. Do not confuse either AdCP polling surface with transport-native MCP/A2A `tasks/*` methods, which use their own task wire shapes. Poll every 2–5 seconds. When the AdCP task `status` is `completed`, the `result` field contains the full `create_media_buy` response with `media_buy_id`. See the [Task lifecycle](/docs/building/by-layer/L3/task-lifecycle) doc for all AdCP task status values. ## Common errors | Symptom | Likely cause | Fix | | ---------------------------------------- | --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- | | HTTP 401 / `error: "invalid_token"` | Expired or wrong API key | Reissue the token from your dashboard; confirm the `Bearer` prefix | | HTTP 401 / `error: "invalid_request"` | `Authorization` header missing | Add `-H "Authorization: Bearer "` to every call | | `errors[]` in body, no `media_buy_id` | Schema validation failure | Read `errors[0].field` and `errors[0].code`; fix the field and retry with a **new** `idempotency_key` | | `status: "submitted"` stays indefinitely | Async task stalled | Check AdCP task status via `get_task_status` or legacy `tasks/get`; if `failed`, read the task error for the rejection reason | | `mcp-session-id: invalid` error | Session expired or header missing | Re-run Step 1 to get a fresh session ID | ## Assessment | Dimension | Weight | What Addie looks for | | ------------------------ | ------ | -------------------------------------------------------------------------------------------- | | Conceptual understanding | 10% | Can you describe the MCP session lifecycle and why `mcp-session-id` is required? | | Practical knowledge | 40% | Can you trace through all five calls in order with correct task names and request shapes? | | Problem solving | 30% | Can you reason through what happens when each step fails or returns an unexpected response? | | Error recovery | 20% | Can you identify the correct fix for auth failures, schema errors, and async polling delays? | Passing threshold: 70%. ## Start this module Open Addie and say "I'd like to start certification module A2B." **Next:** [A3: The AdCP landscape](/docs/learning/foundations/a3-ecosystem-governance)