How to Use the Kustomer MCP in CrewAI

Q: How do I configure the Kustomer MCP inside CrewAI?

Install crewaitools. You can pass the HTTP endpoint directly into your agent's mcps list. The framework automatically parses the available tools and gives them to the agent.

Q: Can I restrict which Kustomer tools my CrewAI agents use?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give your Researcher agent read access via the MCP connection while blocking it from other operations.

Deploy a crew of autonomous support agents. Let CrewAI manage your Kustomer queues without human intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kustomer MCP to CrewAI

Create your Vinkius account to connect Kustomer 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 Kustomer with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Kustomer triage with CrewAI.

Assign the `list_support_conversations` tool to your Watcher agent to stop manually sorting tickets. Build a specialized crew where each agent has a specific job. It constantly monitors the incoming queue for new issues. When a ticket hits, the Watcher passes the ID to the Researcher agent. The Researcher uses `get_conversation_details` and `list_conversation_messages` to read the thread. It summarizes the problem and hands it off to your routing logic.

Deep-dive customer histories autonomously.

Your Investigator agent uses `search_kustomer_timeline` to read past interactions in seconds. Complex enterprise tickets require context. A human takes twenty minutes to read past interactions. Your agent does it instantly. The agent pulls the exact filters it needs as a JSON string and executes the search. It cross-references the results with `get_customer_profile` to figure out if the user is a VIP. The output goes straight to your Slack channel.

Map your support floor dynamically via MCP Server.

Let your setup agent run `list_kustomer_agents` at the start of every shift to map your operational capacity. Hardcoding agent IDs is a fast way to break your automation. Let your crew figure out who is actually working. It builds a live map of your support floor. If you have custom fields, it runs `list_data_klasses` to understand the schema. The rest of your agents use this shared memory to make accurate decisions all day.

Setup guide

Set up Kustomer 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 Kustomer tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai[tools]`. You can pass the HTTP endpoint directly into your agent's `mcps` list. The framework automatically parses the available tools and gives them to the agent.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. You can give your Researcher agent read access via the MCP connection while blocking it from other operations.

Agents share context through their task outputs. The first agent pulls ticket data, and the framework automatically drops that payload into the context window for the next agent in the sequence.

The framework supports Streamable HTTP and SSE out of the box. For cloud deployments, HTTP is usually the most reliable way to connect to external endpoints.

This MCP connection exposes deep timeline events, message bodies, and agent assignments. We isolate the connection entirely. The execution container spins up, runs the specific tool, and instantly terminates, leaving absolutely no trace of your customer records.

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