How to Use the Smarty MCP in CrewAI

Q: What is the optimal workflow for Smarty with crewai?

A strong start is having one agent use extractaddresses on a document. A second agent then takes those results and runs them through the relevant validation tools provided by this MCP Server.

Run autonomous address intelligence with Smarty's MCP Server for your multi-agent crew.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Smarty MCP to CrewAI

Create your Vinkius account to connect Smarty to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Smarty with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Agent Coordination for Location Data

Set up a specialized Agent A to use `extract_addresses` on raw documents. This agent pulls out all possible addresses, giving the data to Agent B. Agent B then validates those strings using either `validate_us_address` or `validate_intl_address`. The crew works together: one agent finds the data; another cleans and verifies it; a third summarizes the final, validated output.

Specialized US Address Validation

Assign a specialized validation role to an agent using `validate_us_address`. This agent's sole job is to confirm Delivery Point Validation (DPV) status and coordinates. It reports the findings back to the main crew memory. The MCP Server ensures that this specific US address check is reliable, making it perfect for focused tasks within your autonomous operations.

Global Address Handling with Smarty

Need global coverage? Define an agent whose role is to validate international addresses. This agent uses `validate_intl_address` and requires the address line plus country for accurate results. If the data seems incomplete, it signals a request back to another agent. The crew handles complex requirements by coordinating different specialized tools like this MCP Server.

Setup guide

Set up Smarty MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Smarty tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Smarty Analyst",
    goal="Access and analyze Smarty data via MCP.",
    backstory="Expert analyst with direct Smarty access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Smarty transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

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

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Smarty Analyst",
        goal="Access and analyze Smarty data via MCP.",
        backstory="Expert analyst with direct Smarty access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Smarty transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Smarty. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Smarty now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Smarty MCP in CrewAI

You assign specific roles and tools from the MCP Server, like `autocomplete_us_address`, to individual agents. The crew coordinates by passing outputs from one agent's tool call as inputs to the next.

The core data type this MCP Server handles is physical address information. This includes US addresses, international street addresses, and general textual location data that needs extraction.

Yes. You can create a sequence where one agent validates ZIP codes (`verify_zip_code`) and another verifies the full address using `validate_us_address` before reporting the final result.

It does. You can build a multi-agent sequence that automatically handles data collection, validation, and error checking without needing human intervention at each step.

A strong start is having one agent use `extract_addresses` on a document. A second agent then takes those results and runs them through the relevant validation tools provided by this MCP Server.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript