How to Use the MarketMan MCP in CrewAI

Q: Can I limit which MarketMan tools a specific CrewAI agent uses?

Yes. Import MCPServerHTTP and apply a toolfilter. You can restrict your accounting agent to only see purchase orders while your chef agent only sees recipes.

Run autonomous restaurant audits with CrewAI. Deploy specialized agents to analyze food costs, track waste, and verify purchase orders.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MarketMan MCP to CrewAI

Create your Vinkius account to connect MarketMan 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 MarketMan with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy a kitchen audit crew

The `list_recipes` tool gives your CrewAI agents exact ingredient breakdowns for menu engineering. You assign one agent to act as the food cost controller. It pulls the recipes and calculates theoretical margins based on current stock prices. A second agent acts as the procurement manager. It uses `list_inventory` to check actual stock against those recipe requirements. They share memory, meaning the controller knows exactly what the purchaser found in the walk-in cooler.

MarketMan MCP Server vendor tracking

The `list_vendors` tool feeds your research agent with supplier contact data. When a delivery runs late, this agent grabs the vendor details and passes them to a response agent. You can add `get_waste_events` into the mix. A separate monitor agent watches the spoilage logs. If a specific vendor's produce rots faster than others, the crew flags that supplier for review. It acts like a digital sous chef watching your back door.

Reconcile orders autonomously

The `list_purchase_orders` tool provides the delivery history to your accounting agent. This agent reads every invoice that came in over the last week. It then pulls `get_count_sheets` to verify the physical inventory. If the kitchen ordered fifty cases of chicken but only counted forty, the crew outputs an exception report. Nobody has to sit in the office matching paper invoices to clipboards.

Setup guide

Set up MarketMan 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 MarketMan tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the server URL directly into the mcps array when defining your agent. Use crewai[tools] to ensure the framework can parse the endpoints correctly.

Yes. Import MCPServerHTTP and apply a tool_filter. You can restrict your accounting agent to only see purchase orders while your chef agent only sees recipes.

It supports stdio, SSE, and Streamable HTTP. Choose the transport that matches your deployment environment for the backend server.

The framework maintains shared memory across the crew. Once the inventory agent fetches the stock counts, the analysis agent can read those numbers without making a second API call.

The endpoints expose raw spoilage quantities and item names. CrewAI runs these queries locally or on your private servers, ensuring your operational inefficiencies never leak to external platforms.

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