How to Use the Afosto MCP in CrewAI

Q: What's the quickest way to use Afosto tools with CrewAI?

It's straightforward. After pip install crewaitools, just pass your unique Vinkius MCP server URL into the mcps list when you define an agent. CrewAI handles the rest.

Q: Can I give different Afosto tools to different agents in my crew?

Yes. For role specialization, import MCPServerHTTP from crewai.mcp. This lets you use a toolfilter to expose only specific tools, like giving listinventory to your logistics agent but not your sales agent.

Q: How do agents in a crew share Afosto data with each other?

CrewAI is designed for collaboration. When one agent calls listcustomers and gets a customer profile from Afosto, it can pass that entire object through CrewAI's shared context to the next agent in the task.

Deploy autonomous agent crews to run your e-commerce operations. Let a specialized CrewAI team manage your Afosto store 24/7.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Afosto MCP to CrewAI

Create your Vinkius account to connect Afosto to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Afosto with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Autonomous Sales Analyst Crew

Get insights without lifting a finger. You can deploy a CrewAI team where one agent's job is to monitor sales by calling `list_orders`. It then passes its findings to a second agent, which uses `list_products` to identify which specific product variants are driving those sales. Because the agents share context, a third 'Writer' agent can take the structured data from the first two and assemble a daily sales report. The entire process runs on its own, giving you a summary every morning.

Deploy a Proactive Inventory Management Team

A single agent can check inventory. A crew can manage it. Assign a 'Monitor' agent to regularly call `list_inventory`. When it detects low stock for a key product, it doesn't just send an alert—it creates a task for a 'Logistics' agent. That second agent can then use `list_orders` to check for large incoming orders that might affect the low-stock item. Based on that context, it can decide whether to escalate the alert or just add it to a weekly restock list. This is how you build an autonomous system that makes informed decisions.

Build a Customer Support Crew with CrewAI

Split up the work for faster, smarter support. When a customer query comes in, a 'Triage' agent can use `list_customers` and `list_orders` to pull the user's complete history from Afosto. It gathers all the necessary context in one place. Instead of trying to solve the problem itself, the Triage agent hands off the neatly packaged information to a specialized 'Resolution' agent. That second agent has everything it needs to solve the customer's problem without asking repetitive questions. It’s a more efficient and intelligent workflow.

Setup guide

Set up Afosto 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 Afosto tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Afosto 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="Afosto Analyst",
        goal="Access and analyze Afosto data via MCP.",
        backstory="Expert analyst with direct Afosto access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Afosto 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 Afosto. 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 Afosto 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 Afosto MCP in CrewAI

It's straightforward. After `pip install crewai[tools]`, just pass your unique Vinkius MCP server URL into the `mcps` list when you define an agent. CrewAI handles the rest.

Yes. For role specialization, import `MCPServerHTTP` from `crewai.mcp`. This lets you use a `tool_filter` to expose only specific tools, like giving `list_inventory` to your logistics agent but not your sales agent.

Absolutely. You can have one agent in your crew whose only job is to watch the `list_orders` tool output. When an order over a certain value appears, it can trigger another agent to send a notification to a private Slack channel.

CrewAI is designed for collaboration. When one agent calls `list_customers` and gets a customer profile from Afosto, it can pass that entire object through CrewAI's shared context to the next agent in the task.

Your Afosto data—customers, orders, and products—is only processed in-memory while the agent performs its task. The Vinkius server provides a sandboxed, ephemeral connection that doesn't store or log any of your business data.

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