How to Use the Customers.ai MCP in CrewAI

Q: How do I restrict tools in CrewAI?

Use the toolfilter configuration to limit access based on agent roles. You give the researcher access to search functions, while only the outreach agent gets permission to send messages. This prevents crossed wires.

Deploy a team of autonomous CrewAI agents to identify anonymous website visitors and execute targeted outreach campaigns.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customers.ai MCP to CrewAI

Create your Vinkius account to connect Customers.ai 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 Customers.ai with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Visitor Identification

Your research agent calls `list_xray_leads` to monitor incoming traffic and identify anonymous website visitors. It runs continuously, scanning for new hits on high-value pages. The agent stores these profiles in shared memory for the rest of the crew to access. Digging deeper into a specific visitor requires the `get_contact` tool. The researcher pulls the full profile and analyzes their company data. This context gets passed directly to your outreach agent for personalized messaging.

Customers.ai MCP Server Contact Sync

A dedicated database agent relies on `search_contacts` to prevent duplicate entries across your systems. It cross-references new visitors against your existing pipeline. When it finds a match, it triggers `update_contact_attributes` to log the new activity. Pipeline organization depends on `add_tag_to_contact` to categorize leads by intent level. If a prospect goes cold, the agent uses `remove_tag_from_contact` to adjust their status. The entire crew coordinates these updates without human intervention.

Multi-Agent Campaign Execution

Firing off an introductory SMS is the job of the `send_text_message` tool. Your outreach agent drafts a highly specific message based on the researcher's findings. A moderator agent can review the text before the tool actually sends it. Delivering complex product catalogs requires `send_rich_message` to push structured JSON payloads. The system monitors the delivery status and adjusts follow-up timing accordingly. You get a fully automated sales development team running 24/7.

Setup guide

Set up Customers.ai 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 Customers.ai tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius HTTP endpoint directly into the mcps array when defining your agent. For advanced setups, use MCPServerHTTP to filter which tools specific agents can access.

Shared memory allows one agent to fetch a lead and another to send the message. The research agent stores the contact ID, and the outreach agent retrieves it instantly. They collaborate exactly like a human sales team.

Use the tool_filter configuration to limit access based on agent roles. You give the researcher access to search functions, while only the outreach agent gets permission to send messages. This prevents crossed wires.

Yes, you can structure your tasks in a strict sequence. The system finds the lead first, updates their CRM record second, and sends the text message last.

The tools process personally identifiable information like names, cell phone numbers, and web activity. Vinkius operates a zero-trust architecture, discarding the execution environment entirely the moment your agent finishes its task.

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