Skip to main content
CrewAI (Python) consumes MCP servers via crewai-toolsMCPServerAdapter, which spawns the server over stdio (or connects over SSE/HTTP) and turns its tools into CrewAI Tool objects.
1

Install

You can skip the global npm install and use npx -y @xentfi/mcp-server as the command instead — slightly slower to start, no PATH setup required.
2

Wire it into a Crew

Letting an agent actually pay

Give a CrewAI agent the xentfi_create_payment tool only if you intend for it to move funds. Because that tool requires confirm: true, a good pattern is a two-agent crew:
  1. Planner agent — decides what payment should happen (recipient, asset, amount) and writes it out, without payment tools.
  2. Executor agent — has only xentfi_create_payment (filter the tool list from xentfi_tools to just this one) and a task instructing it to call it with confirm: true only if the planner’s output passed your own validation step.
This keeps “decide to pay” and “execute the payment” as separately auditable steps in your Crew, on top of XentFi’s own server-side Policy checks.
MCPServerAdapter in newer crewai-tools versions also supports connecting to a remote server over SSE/Streamable HTTP if you’d rather run xentfi-mcp-http centrally and point every Crew at it — see Remote HTTP Deployment and pass the Authorization: Bearer <agent-api-key> header via that adapter’s HTTP params.
Tool names arrive in CrewAI unchanged (xentfi_get_agent_info, etc.) — reference them by name if you filter/allowlist tools per agent.

Next steps

Tools Reference

See every available tool.

Remote HTTP Deployment

Run one shared XentFi MCP endpoint for every Crew.