Join early access
API · AnthropicAgent keyAbout 3 minVerified 2026-10-01

Connect Anthropic Messages API to Pink Agentic AI Payments

Point the Messages API's MCP connector at Pink; Claude calls the payment tools server-side. Works with Agents you build on the Claude API, with no MCP client of your own. Plans: Any API account; MCP connector beta header.

What you get

Anthropic Messages API asks Pink before it pays

Once connected, Anthropic Messages API can see its budget, the payees it may pay and the rules that apply, run a dry run, request a payment and file the receipt. The rules you set in Pink decide each request: allowed on the spot, sent to a person on the phone, or blocked. Anthropic Messages API never holds a card number or a bank login.

Step by step

  1. 1

    Create a free sandbox workspace

    Open agentic-sandbox.pinkwallet.com, type a company name, pick a template (coffee shop, startup or e-commerce) and click Create workspace. You get an admin key for the console and one key per AI agent. Keep the admin key: the sign-in page asks for it.
    After creating a workspace: the admin key and one key per agent are shown once
    After creating a workspace: the admin key and one key per agent are shown once
  2. 2

    Copy an agent key

    On the workspace page or in the console's Keys & connect tab, copy the key of the agent this integration should act as.
    The console's Keys & connect tab with the OAuth URL and the agent keys
    The console's Keys & connect tab with the OAuth URL and the agent keys
  3. 3

    Add Pink to the request

    Send the mcp_servers array with Pink's URL and the agent key as authorization_token, and the beta header anthropic-beta: mcp-client-2025-11-20. Claude discovers the seven tools and calls them during the turn.
  4. 4

    Read the decision

    Tool results come back in the response content. A pending_human decision carries a hold_id; call again later with pink.get_credential or poll GET /v1/payments/{id} from your code.
  5. 5

    Watch the approval land in the console

    Open the sandbox console (link on the workspace page). Requests that cleared, asked a person or were blocked are all listed with the rule that decided them. Approve the pending one and the agent continues.
    Approvals in the console: the rule that stopped the request, the agent's reason, the evidence
    Approvals in the console: the rule that stopped the request, the agent's reason, the evidence

The configuration, ready to paste

Anthropic Messages API · bash
curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: mcp-client-2025-11-20" -H "content-type: application/json" -d '{
    "model": "claude-sonnet-5", "max_tokens": 2000,
    "mcp_servers": [{ "type": "url", "url": "https://agentic-sandbox.pinkwallet.com/mcp", "name": "pink", "authorization_token": "<agent_key>" }],
    "messages": [{ "role": "user", "content": "Reorder 20 kg of espresso beans from Counter Culture Coffee for $420. Check the policy first." }]
  }'

Replace <agent_key> with the key of the agent this api should act as. Each agent has its own key, budget and rules.

Try it: say this to Anthropic Messages API

Say this

“Check my budget with Pink, then order 20 kg of espresso beans from Counter Culture Coffee for $420. After that, order $890 of weekly supplies from Sysco.”

What you will see

The first order is allowed on the spot and the agent receives a single-use test credential. The second stops at the store manager's rule ($500–$2,000): it shows up under Approvals in the console, and the agent waits for a person. Approve it there and the agent picks up the credential.

Why those two rules exist →

Pink's side, in three screens

The sandbox workspace page with the admin key and one key per agent
Keys are shown once when the workspace is created.
Pink's sign-in page: admin key, agent selector, Allow and Deny
Sign-in: choose which agent the app acts as.
The console's Approvals tab with a pending request
Requests that need a person wait here and on the phone.

FAQ

Why a key and not OAuth here?

The API connector takes a pre-acquired token; it does not run a browser sign-in. An agent key is exactly that: a token for one agent.

Can I restrict which tools Claude may call?

Yes, with the tool configuration in the request; for example allow only pink.check_policy for a read-only planning agent.

Official documentation

Menu names and settings paths follow each vendor's documentation at the verified date. If a vendor moves a menu, the linked page is the source of truth; the Pink side does not change.

Other clients