How to Use the Katana MCP in CrewAI

Q: How do I configure the Katana MCP Server in CrewAI?

Run pip install crewaitools. Add the server URL directly to the mcps list when defining your agent, and the framework automatically discovers all eleven tools.

Q: Can I restrict certain Katana tools to specific agents in CrewAI?

You can. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. That way, only your sales agent sees createsalesorder while your inventory agent gets listinventory.

Q: Will my CrewAI agents hallucinate Katana customer IDs?

They might try, but createsalesorder strictly requires a valid customer ID. A smart crew design assigns an agent to run listcustomers first to grab the correct ID before attempting the write.

Q: Does this MCP Server setup support continuous monitoring?

Yes. You can run a background crew that loops through listmanufacturingorders every hour. It alerts your team only when it detects a bottleneck.

Q: How does the Katana CrewAI integration protect material costs?

Your agents process exact material costs and BOMs through listmaterials. Vinkius enforces a zero-trust architecture, authenticating via a single endpoint token and trashing the execution environment the moment your crew finishes its task.

Deploy autonomous Katana manufacturing crews with CrewAI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Katana MCP to CrewAI

Create your Vinkius account to connect Katana 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 Katana with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent ERP Operations

The `list_manufacturing_orders` and `list_materials` tools equip specialized CrewAI agents to manage your factory floor autonomously. A planning agent checks raw materials while a scheduling agent monitors the production queue. You assign distinct roles to each AI. The researcher analyzes `list_products` for upcoming builds, handing off findings to a coordinator that dictates the daily manufacturing schedule without human input.

Automated Order Fulfillment

Your CrewAI setup lets a dedicated sales agent monitor `list_sales_orders` and trigger `create_sales_order` when new requests hit the system. It uses `get_sales_order` to verify the entry immediately after creation. We designed this MCP Server to support hierarchical execution. A manager agent oversees the sales agent, reviewing the customer ID and inventory levels before authorizing the final database write.

Supply Chain Monitoring Crew

Giving a procurement agent access to `list_suppliers` and `list_purchase_orders` creates an autonomous vendor management system. The agent tracks inbound shipments and flags delays directly to your team. If stock dips, the agent queries `get_inventory_by_variant` and drafts a reorder plan. You just pass the server URL into your agent's configuration and watch the crew negotiate the supply chain in real-time.

Setup guide

Set up Katana 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 Katana tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Run `pip install crewai[tools]`. Add the server URL directly to the `mcps` list when defining your agent, and the framework automatically discovers all eleven tools.

You can. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. That way, only your sales agent sees `create_sales_order` while your inventory agent gets `list_inventory`.

They might try, but `create_sales_order` strictly requires a valid customer ID. A smart crew design assigns an agent to run `list_customers` first to grab the correct ID before attempting the write.

Yes. You can run a background crew that loops through `list_manufacturing_orders` every hour. It alerts your team only when it detects a bottleneck.

Your agents process exact material costs and BOMs through `list_materials`. Vinkius enforces a zero-trust architecture, authenticating via a single endpoint token and trashing the execution environment the moment your crew finishes its task.

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