How to Use the Delighted MCP in CrewAI

Q: Can one CrewAI agent search comments while another updates Delighted?

Yes. Your researcher agent can use searchresponsesbycomment to find specific feedback, while your coordinator agent uses addpersontosurvey to schedule follow-up surveys.

Run autonomous CrewAI agent teams to monitor Delighted feedback, analyze NPS trends, and coordinate customer outreach.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Delighted MCP to CrewAI

Create your Vinkius account to connect Delighted 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 Delighted with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent Delighted analysis in CrewAI

The `get_nps_metrics_summary` tool supplies real-time Delighted score breakdowns directly to your CrewAI analyst agent. This CrewAI agent tracks overall shifts in promoter and detractor ratios without needing manual data exports. Once the CrewAI analyst identifies a drop in score, it passes the raw Delighted numbers to a customer success agent in your crew. This second agent uses the data to write targeted retention strategies based on the latest metrics.

Autonomous Delighted detractor triage in CrewAI

The `list_recent_detractors` tool allows your CrewAI monitoring agent to isolate low Delighted NPS scores and flag them for immediate review. The CrewAI agent scans this list hourly to find customers who need urgent attention. A separate responder agent in your CrewAI crew takes those detractor emails and uses `get_person_feedback_history` to pull their full Delighted context. The crew collaborates autonomously to draft personalized recovery plans without human intervention.

Automated Delighted promoter engagement in CrewAI

The `list_top_promoters` tool exposes your highest-scoring Delighted users to your CrewAI marketing agent. The CrewAI agent uses this list to find advocates who are prime candidates for case studies or referral programs. By combining this with `get_response_details`, the CrewAI agent reviews what specific features the Delighted promoters praised. Your crew then builds tailored outreach campaigns based on the exact words your happiest customers used.

Setup guide

Set up Delighted 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 Delighted tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server's URL directly into your CrewAI Agent definition using the `mcps` array parameter, giving your specialized agents instant access to tools like `list_survey_responses`.

Yes. Your researcher agent can use `search_responses_by_comment` to find specific feedback, while your coordinator agent uses `add_person_to_survey` to schedule follow-up surveys.

All customer email addresses and survey feedback comments processed by your crew are kept in transient memory. The MCP Server executes in an isolated V8 sandbox, preventing any persistent storage or leakage of your Delighted customer records.

Yes. Set up a hierarchical crew where a manager agent continuously polls `get_recent_customer_comments` via the MCP protocol and assigns follow-up tasks to subordinate agents based on customer sentiment.

Your customer email addresses and NPS scores are processed in transient memory. The connection to the MCP endpoint runs through a secure channel that prevents third parties from viewing your Delighted 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