How to Use the Refiner MCP in CrewAI

Q: Can I restrict which Refiner MCP Server tools a CrewAI agent can use?

Yes, you can use MCPServerHTTP along with a toolfilter to only expose safe read tools like listrefinersegments while blocking write tools like identifyrefineruser.

Q: How can I verify the connection in my Python script?

You can have a starter task run checkrefinerstatus. If the task succeeds, your crew knows the API is live and can proceed with analyzing surveys and updating contacts.

Q: How does CrewAI protect the privacy of our user segments?

Your user segments accessed via listrefinersegments are processed entirely in memory during the crew's execution. Vinkius runs the underlying MCP Server in an ephemeral sandbox, leaving no persistent footprint of your user data.

Deploy a crew of specialized agents using CrewAI and this MCP Server to analyze Refiner feedback.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Refiner MCP to CrewAI

Create your Vinkius account to connect Refiner 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 Refiner with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent NPS Analysis with CrewAI

Instead of one agent doing everything, CrewAI lets you split the work. This MCP Server lets you split tasks: a research agent uses `list_refiner_responses` to pull recent NPS scores, while an analyst agent categorizes the qualitative text feedback into feature requests and bug reports. This multi-agent setup uses shared memory to keep context across tasks. The agents collaborate to isolate high-value accounts that left poor scores, ensuring your product team gets a curated list of issues that actually matter.

Autonomous User Profile Enrichment

Let your crew keep your CRM and survey tools in sync without human intervention. An operations agent can run `list_refiner_contacts` to find profiles missing key company details, then pass those contacts to a research agent. Once the research agent finds the missing data, a third agent uses `identify_refiner_user` to update the profile in Refiner. You can configure this using standard CrewAI sequential execution to run every night.

Targeted Survey Distribution by CrewAI

Stop blasting surveys to every user at random times. Your CrewAI agents can analyze product usage patterns and call `list_refiner_surveys` to find the right in-app questionnaire for a specific user cohort. The crew then triggers `track_refiner_event` to fire the exact event that prompts the micro-survey in your web app. This ensures your NPS and feedback prompts only appear when users are highly engaged.

Setup guide

Set up Refiner 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 Refiner tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The easiest way is passing your Vinkius HTTP endpoint URL directly into the `mcps` array when initializing your CrewAI agent. The framework handles the tool discovery and registration automatically.

Yes, you can use `MCPServerHTTP` along with a `tool_filter` to only expose safe read tools like `list_refiner_segments` while blocking write tools like `identify_refiner_user`.

CrewAI manages task execution sequentially or hierarchically. This prevents your agents from spamming `track_refiner_event` simultaneously and helps you stay within your API rate limits.

You can have a starter task run `check_refiner_status`. If the task succeeds, your crew knows the API is live and can proceed with analyzing surveys and updating contacts.

Your user segments accessed via `list_refiner_segments` are processed entirely in memory during the crew's execution. Vinkius runs the underlying MCP Server in an ephemeral sandbox, leaving no persistent footprint of your user data.

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