Built for Agents

The Interchange API is built from the ground up for AI agents. Both humans and agents share the same surface: a REST API and a generic MCP wrapper that exposes the entire surface through three tools — no per-domain tool sprawl, no SDK, no glue code.

Why agent-first

Same surface for humans and agents

REST and MCP expose an identical featureset against the same OpenAPI — no parallel “AI surface” to drift out of sync. See Philosophy for the SESOFI pattern (Single Endpoint, Single Object, Full Intent) that keeps composite intents legible.

Generic MCP wrapper

Three tools (health, ask_about_capability, api_call) cover every endpoint. Adding a new REST endpoint instantly makes it agent-callable — no new MCP tool to write, register, or deploy.

Declarative tool surface

A single skill.md URL teaches an agent the entire API. ask_about_capability queries it on demand, so agents discover endpoints instead of memorizing them.

Role-aware

Buyer and storefront roles each get their own skill file and OpenAPI spec, so agents see only the surface relevant to the caller.

Supported AI agents

Claude (Claude.ai Team/Enterprise, Claude Desktop, Claude Code)
ChatGPT (MCP Connectors and Custom GPTs)
Cursor
Custom agents — anything that speaks MCP or HTTP

Per-agent setup details are below; the Quickstart is a one-page index that links here.

Connection Methods

REST API

Standard HTTP REST API for traditional integrations:

Environment	Buyer Base URL	Storefront Base URL
Production	`https://api.interchange.io/api/v2/buyer`	`https://api.interchange.io/api/v2/storefront`

MCP (Model Context Protocol)

For AI agent integrations using JSON-RPC 2.0:

Environment	Buyer MCP Endpoint	Storefront management MCP	Canonical Storefront Agent URL
Production	`https://api.interchange.io/mcp/buyer`	`https://api.interchange.io/mcp/storefront`	`https://interchange.io`

The REST URLs are pinned to v2 and will keep serving v2 even after a future major version ships. The buyer and storefront-management MCP URLs are unversioned aliases that auto-redirect to whatever is currently stable (today: v2). The canonical storefront agent URL is an identity publishers list in adagents.json; it is not the operator’s management connector. See Versioning for when to use each.

Available MCP Tools

Each MCP endpoint exposes three core tools that cover the entire API surface:

Tool	Purpose
`health`	Check API health and verify connectivity
`ask_about_capability`	Query the skill documentation to discover endpoints and their schemas
`api_call`	Make authenticated REST API calls to any endpoint

Workflow: an agent first uses ask_about_capability to learn what endpoints exist, then uses api_call to execute them.

Automating storefront setup

A storefront operator can connect Claude Code, Codex, Cursor, or another MCP client to:

https://api.interchange.io/mcp/storefront

Authenticate as a user or API key on the storefront account. The connector can use ask_about_capability to discover setup and product operations, then api_call to read or change the same storefront resources available over REST. For example, it can inspect inventory, draft and bulk-create products from an attached spreadsheet, configure buyer routing, and check readiness. Mutating operations retain the same authorization and confirmation requirements as the rest of Interchange. For Codex, register the HTTP connector and complete its OAuth login:

codex mcp add interchange-storefront --url https://api.interchange.io/mcp/storefront
codex mcp login interchange-storefront

For headless automation, set an API key in an environment variable and register it with --bearer-token-env-var instead of putting the key in shell history. This operator connector is separate from the buyer-facing AdCP endpoint at https://api.interchange.io/storefront/{platformId}/mcp. A hosted storefront exposes that endpoint when it is configured to advertise as an agent. An external buyer agent authenticates with entitled Interchange buyer credentials; there is no separate seller-side connection handshake. Submitted media buys follow the storefront’s media-buy approval mode and acceptance policy, including any configured per-buyer auto-approval. See Approvals. Both endpoints also expose a conversational assistant tool when it is enabled for your account:

Tool	Purpose
`ask_murph`	Ask Murph, your AI guide to Interchange, a plain-English question — “how do I…”, “why is my campaign in this state”, “what changed recently” — or file a support report

ask_murph is available once the assistant is enabled for your account. If it is not yet turned on, the call returns a friendly “not enabled” message instead of an answer — contact Interchange support to enable it. Use ask_murph for guidance and support, and the three core tools (api_call et al.) for actual reads and mutations.

Connecting AI Agents

Claude Connector (Claude.ai Team / Enterprise)

This is the recommended way to connect Claude to Scope3. It provides OAuth-based authentication and works across both Claude.ai (browser) and Claude Desktop automatically.

Admin Setup (one-time):

Go to claude.ai → Admin Settings → Integrations → MCP Connectors
Click Add Connector
Enter the MCP endpoint URL: https://api.interchange.io/mcp/buyer
Name it (e.g., “Interchange API”)
Save the connector — it is now available to all members in your organization

User Setup:

Go to claude.ai → Settings → Integrations → MCP Connectors
Find the Scope3 connector and click Connect
Log in with your Scope3 credentials when prompted (OAuth)
Start chatting! Ask Claude: “List my advertisers” or “Create a performance campaign”

Once connected via the connector, it works in both Claude.ai (browser) and Claude Desktop. No separate configuration needed.

Claude Desktop (Personal / Manual Setup)

If you don’t have a Claude Team or Enterprise plan, you can connect Claude Desktop directly via OAuth. Edit your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "scope3-buyer": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.interchange.io/mcp/buyer"]
    }
  }
}

Restart Claude Desktop. The first call opens a browser for you to sign in to Interchange — mcp-remote caches the OAuth token afterward. If you need to use an API key instead (CI, headless environments), pass it as a header:

{
  "mcpServers": {
    "scope3-buyer": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.interchange.io/mcp/buyer",
        "--header",
        "Authorization: Bearer scope3_your_api_key_here"
      ]
    }
  }
}

Claude Code (CLI)

OAuth (recommended — no key to manage):

claude mcp add --transport http scope3-buyer https://api.interchange.io/mcp/buyer
claude

The first call to the server opens a browser to sign in to Interchange. Claude Code caches the token after that. API key (CI, headless, or if you can’t open a browser): pass the header on registration. Claude Code’s HTTP transport doesn’t read environment variables, so the API key must be set as a header here.

claude mcp add --transport http scope3-buyer https://api.interchange.io/mcp/buyer \
  --header "Authorization: Bearer scope3_your_api_key_here"
claude

Then ask: “Use ask_about_capability to learn how to list advertisers, then use api_call to list them” Once connected, Claude Code can also talk to Murph directly through the same server — no extra setup. Just ask a question in plain English and Claude Code will call the ask_murph tool:

Ask Murph why my campaign is still in PENDING

Ask Murph how to register credentials for a sales agent

Murph keeps its own conversation thread (returned as conversationUid in the tool result); follow-up questions in the same Claude Code session continue that thread. ask_murph is for guidance and support — for actual reads or mutations, Claude Code uses api_call.

ChatGPT

Important: ChatGPT MCP connectors use OAuth authentication only. Custom headers like x-scope3-api-key are not supported. Authentication is handled automatically through the OAuth login flow.

MCP Connector
Custom GPT

Connect ChatGPT to Scope3 via MCP:

Go to ChatGPT → Settings → MCP Connectors
Click Add Connector
Enter MCP Server URL: https://api.interchange.io/mcp/buyer
Select OAuth as the authentication method
Complete the Scope3 login flow when prompted
Once connected, you’ll have access to 3 tools:
- health - Check API status
- ask_about_capability - Learn about available endpoints
- api_call - Make authenticated API calls
Test with: “Use ask_about_capability to learn how to list advertisers”

Create a Custom GPT with OAuth:

Go to ChatGPT → My GPTs → Create a GPT
Go to Configure → Actions → Create new action
Import the OpenAPI spec:
- Click Import from URL
- Enter: https://api.interchange.io/api/v2/buyer/openapi.yaml
Set up OAuth authentication:
- Authentication type: OAuth
- Client ID: Register the redirect URI ChatGPT shows for your action through /auth/register, then paste the returned client_id.
- Authorization URL: https://api.interchange.io/authorize
- Token URL: https://api.interchange.io/auth/token
- Scope: openid profile email
Save and test with: “List all my advertisers”

Custom browser agents

If your agent runs in a browser you control, configure two separate allowlists. They solve different problems and the values are intentionally different:

Setting	What to register	Why
OAuth redirect URI	The full callback URL, including path, for example `https://mcp.example.com/oauth/callback`	OAuth sends the user back here after login. The callback must match exactly.
Browser origin	The exact origin only, for example `https://mcp.example.com`	CORS allows browser calls from this origin to MCP/OAuth endpoints. Do not include paths, queries, fragments, or wildcards.

1. Register the OAuth redirect URI

curl -X POST https://api.interchange.io/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "client_name": "Example Agent",
    "redirect_uris": ["https://mcp.example.com/oauth/callback"]
  }'

The response includes a generated client_id. Use that client_id when starting OAuth. Register every callback URL your agent will use, including the path; https://mcp.example.com/oauth/callback and https://mcp.example.com/callback are different redirect URIs. Redirect URI rules:

Production redirect URIs must use https://.
Local development callbacks may use localhost redirect URIs.
Redirect URIs must not include fragments (#...) or embedded usernames/passwords.
Dynamic registration creates a public OAuth client for PKCE (token_endpoint_auth_method: "none"). Do not treat the generated client_id as a secret.
Registering a redirect URI does not by itself authorize a browser agent for an account. For self-serve clients, Interchange issues an authorization code only when the redirect origin has also been approved for the authenticated account.

2. Add the browser origin for CORS

If your custom agent shows “An account admin must add this browser origin before authorizing this MCP client,” an account admin needs to register that origin here first.

Account admins can add, view, and remove browser origins from Interchange → API Keys → Browser origins, or manage them programmatically. Through the shared v2 API:

curl -X POST https://api.interchange.io/api/v2/browser-origins \
  -H "Authorization: Bearer scope3_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "origin": "https://mcp.example.com",
    "label": "Example Agent"
  }'

You can also manage these origins through MCP by asking an authenticated agent to call list_browser_origins, create_browser_origin, or delete_browser_origin. Only account admins can list, create, or delete origins. Browser origin rules:

Register only the origin: scheme://host[:port].
Origins must use https://.
Do not include paths, query strings, fragments, or wildcards.
Register each environment separately, for example production and staging agent hosts.

Security posture

Account-managed browser origins are exact-match and only apply to these browser MCP/OAuth paths: /authorize, /auth/register, /auth/token, /auth/mcp/authorize, /.well-known/*, /mcp, and /mcp/*. They do not open the full REST API to that origin. Dynamic client registration is public so MCP clients can discover and register themselves, but account access is still gated by login, PKCE, exact redirect URI matching, and the account-approved browser origin check. Account-managed origins also do not receive credentialed cookie CORS. Interchange returns Access-Control-Allow-Origin for allowed MCP/OAuth browser calls, but it does not return Access-Control-Allow-Credentials for account-managed origins. Browser agents should use OAuth access tokens or explicit bearer tokens, not Interchange UI cookies. First-party Interchange UI origins continue to use credentialed CORS. If a browser request is blocked:

Confirm the OAuth redirect URI is the full callback URL and was registered through /auth/register.
Confirm the browser origin is only the origin and was added by an account admin.
Confirm the request is going to one of the supported browser MCP/OAuth paths, not an arbitrary REST endpoint.
Confirm the browser request does not require cookies or credentials: "include".

Cursor

Configure Cursor with the Scope3 MCP server:

Open Cursor Settings → MCP tab
Add a new MCP server:
- Name: scope3
- URL: https://api.interchange.io/mcp/buyer
- Headers: Authorization: Bearer your-api-key
Restart Cursor
In chat, ask: “Use Scope3 tools to list advertisers”

What the server tells your agent on connect

Every MCP session starts with operating instructions the server sends during the handshake. Your agent receives them automatically — nothing to configure — and they are the same rules our own assistant follows. Knowing what is in them tells you what behaviour to expect, and what to preserve if you wrap our tools in your own harness. For a storefront connection: Orient before acting. Call get_storefront_readiness for the current configuration state and what is blocking the storefront from transacting, rather than reconstructing it from a series of list calls. Look up the operation before calling it. api_call takes a named operation; there is no raw method-and-endpoint mode, and an invented name is rejected. Call ask_about_capability first for the exact operation name and field shapes. Prefer a typed tool where one exists. Route explanation to Murph. “How do I…”, “why is my X stuck in state Y”, “what changed recently” and “I think this is broken” go to ask_murph, which searches the published documentation, inspects live storefront state, and can file an internal report. Murph is read-only; mutations stay on api_call or a typed tool. One mutating call per turn. Make one write, present the result, then stop and wait for the user. Verify success before reporting it. A call succeeded only if the status is 2xx and the payload carries the endpoint’s success indicator — a returned id, the updated resource, an empty 204. A 202 means queued, not done: report it as kicked off and surface the operation id. If the indicator is missing or contradicts success, surface the error verbatim and do not say the change was made. Do not answer publisher authorization from memory. Whether a domain needs an adagents.json entry, and what belongs in it, depends on how that inventory is sold. Look it up through Murph or the published documentation, or read live state via open_property_roster — see Identity documents. State only what the data shows. If a tool returns no results, say so rather than speculating about why. Never claim a connection, authorization, or status exists unless a tool response contains it.

Authentication

Use OAuth for Claude/ChatGPT MCP connectors (handled automatically) or an API key (Authorization: Bearer scope3_...) for CLIs, Cursor, and custom agents. See Authentication for full details.

Notifications

The API surfaces unread notifications inline in ask_about_capability responses, so agents can proactively flag campaign or creative issues to users. See the Notifications guide for setup and the REST endpoints.

Next Steps

Quickstart

Connect Claude, ChatGPT, Cursor, or a custom agent in minutes.

Buyer Onboarding

The end-to-end campaign-launch journey for buyer integrations.

Skill

What skill.md is and how agents use it for capability discovery.

Authentication

API keys, OAuth, and SSO configuration.

Welcome

Core Concepts

Connect

Cross-Cutting Reference

Release Notes

Why agent-first

Same surface for humans and agents

Generic MCP wrapper

Declarative tool surface

Role-aware

Supported AI agents

Connection Methods

REST API

MCP (Model Context Protocol)

Available MCP Tools

Automating storefront setup

Connecting AI Agents

Claude Connector (Claude.ai Team / Enterprise)

Claude Desktop (Personal / Manual Setup)

Claude Code (CLI)

ChatGPT

Custom browser agents

1. Register the OAuth redirect URI

2. Add the browser origin for CORS

Security posture

Cursor

What the server tells your agent on connect

Authentication

Notifications

Next Steps

Quickstart

Buyer Onboarding

Skill

Authentication

​Why agent-first

Same surface for humans and agents

Generic MCP wrapper

Declarative tool surface

Role-aware

​Supported AI agents

​Connection Methods

​REST API

​MCP (Model Context Protocol)

​Available MCP Tools

​Automating storefront setup

​Connecting AI Agents

​Claude Connector (Claude.ai Team / Enterprise)

​Claude Desktop (Personal / Manual Setup)

​Claude Code (CLI)

​ChatGPT

​Custom browser agents

​1. Register the OAuth redirect URI

​2. Add the browser origin for CORS

​Security posture

​Cursor

​What the server tells your agent on connect

​Authentication

​Notifications

​Next Steps

Quickstart

Buyer Onboarding

Skill

Authentication

Why agent-first

Supported AI agents

Connection Methods

REST API

MCP (Model Context Protocol)

Available MCP Tools

Automating storefront setup

Connecting AI Agents

Claude Connector (Claude.ai Team / Enterprise)

Claude Desktop (Personal / Manual Setup)

Claude Code (CLI)

ChatGPT

Custom browser agents

1. Register the OAuth redirect URI

2. Add the browser origin for CORS

Security posture

Cursor

What the server tells your agent on connect

Authentication

Notifications

Next Steps