How to Use the CleverTap MCP in CrewAI

Q: How can a CrewAI team analyze CleverTap campaigns?

Define two agents. Give the first one the listclevertapcampaigns tool to find campaigns, and give the second one the getcampaignperformancereport tool to analyze them. Create a sequential task where the first agent's output becomes the second agent's input.

Q: Can I limit which CleverTap tools a specific CrewAI agent can use?

Yes. When you set up the MCPServerHTTP connection in CrewAI, use the toolfilter argument. This lets you assign specific tools, like getuserprofiledetails, only to the agents that absolutely need them, enforcing the principle of least privilege.

Q: What's the easiest way to give my CrewAI agents access to CleverTap?

For a quick start, just pass your Vinkius MCP URL into the mcps list when you define your agent. CrewAI will automatically discover and register all the available CleverTap tools for that agent to use.

Assemble an autonomous AI team to manage your CleverTap account with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CleverTap MCP to CrewAI

Create your Vinkius account to connect CleverTap 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 CleverTap with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create an Autonomous Analytics Crew

Assign specialized roles to your CrewAI agents. A "Metric Analyst" agent can use `get_campaign_performance_report` to pull raw performance data. It then hands that data off to a "Strategist" agent who interprets the results and suggests what to do next. The agents share their work in a shared memory space. A final "Reporter" agent can take the Strategist's findings and write a summary. It's a collaborative report generated by a team of agents working with real CleverTap data.

Proactive Account Monitoring

Set up a "Monitor" agent whose only job is to run checks. It can use `get_real_time_usage_stats` to watch for traffic spikes or `list_event_schemas` to detect unexpected changes to your event tracking. This agent is your first line of defense. When the Monitor agent finds an issue, it passes the task to a "Responder" agent. That agent can then use `get_user_profile_details` to investigate affected users or notify a human operator. The whole process runs without your intervention.

Data Auditing with a CrewAI MCP Server

Your crew can perform complex audits that would be tedious for a person. An "Auditor" agent can `list_clevertap_apps`, then for each app, use `list_user_profile_properties` to make sure your data schema is consistent across the entire account. You can set up a hierarchical crew where a "Manager" agent delegates tasks. It might tell one agent to fetch all campaigns with `list_clevertap_campaigns` and another to get all segments with `list_clevertap_segments`, then compare the two lists. The MCP server provides the tools for each specialist agent to do its job.

Setup guide

Set up CleverTap 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 CleverTap tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Define two agents. Give the first one the `list_clevertap_campaigns` tool to find campaigns, and give the second one the `get_campaign_performance_report` tool to analyze them. Create a sequential task where the first agent's output becomes the second agent's input.

Yes. When you set up the `MCPServerHTTP` connection in CrewAI, use the `tool_filter` argument. This lets you assign specific tools, like `get_user_profile_details`, only to the agents that absolutely need them, enforcing the principle of least privilege.

For a quick start, just pass your Vinkius MCP URL into the `mcps` list when you define your agent. CrewAI will automatically discover and register all the available CleverTap tools for that agent to use.

Absolutely. Assign a "Monitoring" agent the task of periodically calling `get_real_time_usage_stats`. If it detects an anomaly, it can delegate a new task to an "Incident" agent to investigate or alert your team.

Access to user profile data is controlled by which agent has the `get_user_profile_details` tool. The MCP server itself processes data in-memory within single-use, sandboxed environments. Nothing is logged or stored by Vinkius, which keeps your CleverTap user data confidential.

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