How to Use the Kyte MCP in CrewAI

Q: How do I add the Kyte MCP Server to my CrewAI agent setup?

Install crewaitools and pass your Vinkius endpoint directly into the mcps array on your Agent definition.

Q: Can CrewAI agents filter Kyte tools selectively?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. This restricts specific agents to only the tools they actually need.

Deploy specialized agents to manage your Kyte store operations using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kyte MCP to CrewAI

Create your Vinkius account to connect Kyte 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 Kyte with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Stock Levels Autonomously

Assign an inventory agent to monitor `get_inventory_status` and `get_product_details` continuously through this MCP integration. This specialized worker watches your stock levels hour by hour. When specific items dip below your defined threshold, this agent alerts a secondary purchasing agent. They collaborate to draft reorder requests without you lifting a finger.

Audit Financial Records with this MCP Server

Build an autonomous auditing team powered by this Kyte MCP Server by assigning one agent to pull daily records via `list_financial_transactions`. This worker grabs the raw accounting data and passes it to the next phase. A second agent takes those records and verifies the delivery statuses using `get_order_details`. They cross-reference the data in shared memory and output a daily reconciliation report without human oversight.

Deploy Customer Success Crews

Create a customer success crew that triggers when `get_kyte_store_status` shows the shop is open. The moderator agent initiates the sequence the moment the doors unlock. It pulls a list of recent buyers with `list_kyte_customers` and assigns a support agent to review each `get_customer_profile`. The crew automatically drafts follow-up emails for high-ticket purchases.

Setup guide

Set up Kyte 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 Kyte tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai[tools]` and pass your Vinkius endpoint directly into the `mcps` array on your Agent definition.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. This restricts specific agents to only the tools they actually need.

They use shared memory. The auditing agent fetches the order list, and the reporting agent reads that exact data from the crew's context window.

You configure your crew to run sequentially or hierarchically on a cron job. The agents wake up, check the stock, and go back to sleep.

We handle authentication centrally and run your requests in isolated V8 sandboxes. Your financial records and customer profiles never touch persistent storage on our end.

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