How to Use the Junip MCP in CrewAI

Q: Can this CrewAI setup help optimize our active Junip campaigns?

Yes, your marketing crew can use listcampaigns to audit active review requests. The agents compare campaign performance against your store's active layout from listthemes to suggest the best times to ask customers for feedback.

Deploy a collaborative team of CrewAI agents to manage your Junip reviews and customer questions using 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 Junip MCP to CrewAI

Create your Vinkius account to connect Junip 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 Junip with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent review auditing with CrewAI

One agent isn't enough to manage a busy storefront. With CrewAI, you set up a team where one agent monitors brand sentiment and another handles customer recovery. The first agent calls `list_reviews` to find critical feedback. When a 1-star review is found, the researcher agent hands the data to a resolver agent. That agent uses `get_review` to pull specific customer metadata. It analyzes the complaint and creates a recovery plan without human intervention.

Coordinate store questions and merchant replies

Build an autonomous customer support crew. Your researcher agent scans `list_questions` to find new inquiries. It then passes the raw text to an expert writer agent who is trained on your brand voice. The writer agent uses `list_answers` to match the tone of past replies. Checking `get_product` ensures the technical details are correct. Together, they draft a precise response, keeping your Q&A section clean and helpful.

Analyze campaign impact across your store

Let your marketing agents evaluate your review collection strategies. A CrewAI analyst agent calls `list_campaigns` to see which email sequences are active. It coordinates with another agent checking store presentation. The second agent calls `list_themes` to confirm the review widgets match the current store design. By comparing active campaigns with review volume, the crew recommends styling changes to maximize your response rates.

Setup guide

Set up Junip 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 Junip tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius HTTP endpoint URL directly into the agent's `mcps` list. CrewAI automatically discovers the tools like `list_reviews` and `get_product`. This MCP Server lets your specialized agents invoke them during their collaborative tasks.

Yes, CrewAI is designed for multi-agent collaboration. A researcher agent can fetch a bad review with `get_review` using our MCP tool, then pass the details to a support agent. The support agent then drafts a reply based on the product details.

You can set rate limits on your CrewAI agents or restrict tool access using a tool filter. This prevents agents from calling `list_questions` repeatedly. Vinkius also manages the underlying API connection to prevent rate-limiting blocks.

Yes, your marketing crew can use `list_campaigns` to audit active review requests. The agents compare campaign performance against your store's active layout from `list_themes` to suggest the best times to ask customers for feedback.

All interactions are processed within a zero-trust V8 sandbox on Vinkius. The MCP Server connection is ephemeral, keeping your e-commerce data secure. Your Junip product reviews, campaigns, and questions are never stored or used to train public models.

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