Connect CrewAI to Pink Agentic AI Payments

What you get

CrewAI asks Pink before it pays

Once connected, CrewAI 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. CrewAI 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.

   

2. 2

   Copy an agent key

   From the workspace page or the console.

   

3. 3

   Open the adapter

   Create an MCPServerAdapter with url https://agentic-sandbox.pinkwallet.com/mcp, transport streamable-http and the Authorization header; use it as a context manager and pass its tools to the agent.
4. 4

   Kick off the crew

   Describe the purchase in the task and run kickoff().
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.

   

The configuration, ready to paste

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter

with MCPServerAdapter({"url": "https://agentic-sandbox.pinkwallet.com/mcp", "transport": "streamable-http",
                        "headers": {"Authorization": "Bearer <agent_key>"}}) as tools:
    buyer = Agent(role="Purchasing AI", goal="Keep the kitchen stocked inside the payment policy", backstory="Coffee shop procurement agent", tools=tools)
    task = Task(description="Reorder 20 kg of espresso beans from Counter Culture Coffee for $420. Check the policy, request the payment, file the receipt.", expected_output="Decision and payment id", agent=buyer)
    Crew(agents=[buyer], tasks=[task]).kickoff()

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

Try it: say this to CrewAI

Pink's side, in three screens

Official documentation

• CrewAI: MCP servers as tools ↗
• Pink: the seven MCP tools, with real responses
• Pink: security model (what the client can and cannot reach)

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