How to Use the Custify MCP in CrewAI

Q: How do I restrict which Custify tools my CrewAI agents can use?

Import MCPServerHTTP and use the toolfilter configuration. This lets you expose specific operations to specific roles.

Deploy autonomous agent crews to monitor customer health scores and execute retention playbooks using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Custify MCP to CrewAI

Create your Vinkius account to connect Custify 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 Custify with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy specialized customer success agents

Single agents struggle to handle both deep data analysis and targeted outreach simultaneously over an MCP connection. Forcing one model to monitor health scores while also writing emails results in hallucinations. Splitting these tasks across a specialized team fixes the problem. You assign `list_health_scores` and `list_companies` to a dedicated research agent. This analyst constantly monitors your base and passes flagged accounts into shared memory, where a separate moderator agent decides how to intervene.

Execute autonomous retention via MCP Server

Manual churn prevention relies on human teams noticing a drop in activity before the renewal date. That reactive approach guarantees lost revenue. Autonomous crews operate continuously in the background. When the monitor agent detects a negative trend, the action agent steps in. It pulls full context via `get_person_details` and fires off `track_user_event` to trigger a re-engagement sequence, completely without human intervention.

Filter tool access by agent role

Giving every agent in your crew full write access to your CRM is dangerous. A junior research agent should never have the ability to modify account records or trigger billing events by mistake. Using the tool_filter parameter, you restrict the analyst to read-only operations like `list_user_segments`. You only expose `create_person` to the senior execution agent, ensuring strict boundaries within your autonomous pipeline.

Setup guide

Set up Custify 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 Custify tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius endpoint directly into the mcps array on your Agent definition. The framework automatically loads all available operations.

Yes. Your analyst agent and execution agent can both access the endpoint, passing context back and forth through the framework's shared memory.

Import MCPServerHTTP and use the tool_filter configuration. This lets you expose specific operations to specific roles.

The MCP architecture works perfectly with manager agents. A manager can evaluate the output of a data pull and delegate follow-up tasks to subordinates.

Every API request requires a single endpoint token managed by Vinkius. When your crew fetches product user lists or health scores, the transaction occurs within a secure V8 isolate that shuts down immediately after execution.

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