How to Use the Uniqode MCP in CrewAI

Q: What if I need to track analytics data using Uniqode and CrewAI?

You assign a 'Tracking Agent' role. This agent calls getanalyticslocation or getanalyticstime. The moderator then reviews the resulting dataset, ensuring that all necessary metrics were collected.

Run autonomous operations on QR code tracking and marketing data using the CrewAI agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Uniqode MCP to CrewAI

Create your Vinkius account to connect Uniqode 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 Uniqode with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Code Inventory and Updates

You can build a specialized 'Auditor' agent that runs `list_qrcodes` to gather all codes. A second 'Updater' agent then takes the list, identifies outdated entries using `get_qrcode`, and executes `update_qrcode`. This is sequential execution in action. The shared memory allows agents to pass context—like an organization ID from `list_organizations`—between roles, ensuring that every single tool call operates within the correct scope.

Complex Marketing Data Analysis with MCP Server

The 'Analyst' agent can gather marketing data by calling `list_campaigns`. It then coordinates calls to both `get_analytics_location` and `get_analytics_time` to create a complete picture. The moderator agent watches this process. Because the tools are exposed as specialized roles, you don't worry about function signatures or async management; CrewAI handles that complexity for autonomous operation.

Structured Reporting and Tagging

Define a 'Reporter' agent whose job is to gather raw data by calling `list_tags` and `list_folders`. This agent then passes the resulting tags/folders list to another specialized agent that uses it for context when performing actions like `create_qrcode`. The hierarchical execution lets you model real business processes, like 'First find all folders, then create a code inside them.'

Setup guide

Set up Uniqode 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 Uniqode tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You define a specialized agent whose role is 'Code Creator.' This agent uses `create_qrcode` after consulting the shared memory for necessary parameters like `list_organizations`. The system handles the entire lifecycle automatically.

Yes. You can have a 'Data Collector' agent call multiple tools—like `get_account_info`, then `list_tags`, and finally `list_qrcodes`—in sequence, building one cohesive report from the gathered results.

You assign a 'Tracking Agent' role. This agent calls `get_analytics_location` or `get_analytics_time`. The moderator then reviews the resulting dataset, ensuring that all necessary metrics were collected.

Sure. A specialized 'Maintenance' agent can be tasked solely with calling `update_qrcode` on a list of IDs retrieved by the initial `list_qrcodes` call.

It touches account details and scan analytics. The server processes location coordinates (`get_analytics_location`), which is considered sensitive user behavior information.

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