How to Use the GoSquared MCP in CrewAI

Q: Can a CrewAI agent share GoSquared data with another agent?

Yes, CrewAI's shared memory allows an agent using getnowoverview to pass traffic metrics to a content writing agent. The second agent can then draft social media posts tailored to the active audience.

Q: How do I limit which GoSquared tools a CrewAI agent can use?

You can use the MCPServerHTTP class from the framework's MCP module and apply a tool filter. This restricts a research agent to gettrendspages while blocking them from real-time operational tools.

Deploy a crew of specialized AI agents to analyze and react to live GoSquared traffic 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 GoSquared MCP to CrewAI

Create your Vinkius account to connect GoSquared 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 GoSquared with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Traffic Monitoring

The `get_now_visitors` tool provides your monitoring agent with a real-time list of active sessions. This agent tracks visitor behavior patterns and passes anomalous spikes to an analysis agent for deeper inspection. The analysis agent then uses `get_now_pages` to determine which content is keeping those visitors engaged. This collaborative crew works autonomously, letting you monitor site engagement without staring at a dashboard all day.

Autonomous Campaign Optimization

The `get_now_campaigns` tool allows your marketing agent to track active promotional campaigns in real-time. If a campaign underperforms, the agent alerts a media buying agent to adjust ad spend. To make informed decisions, the media buyer agent queries `get_trends_campaigns` to compare current performance against historical baselines. This prevents knee-jerk reactions to temporary traffic dips by providing long-term context.

Technical Audits via CrewAI MCP Server

The `get_trends_overview` tool gives your research agent a high-level view of historical traffic patterns. The agent analyzes these patterns to identify seasonal trends and shifts in baseline traffic. Simultaneously, a developer agent uses `get_trends_browsers` and `get_trends_devices` to check for technical bottlenecks. They collaborate to produce a weekly audit detailing how device shifts affect your overall traffic volume.

Setup guide

Set up GoSquared 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 GoSquared tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server URL directly in your agent's configuration using the MCP server integration. This grants specific agents access to tools like `get_now_sources` while keeping other agents focused on non-analytical tasks.

Yes, CrewAI's shared memory allows an agent using `get_now_overview` to pass traffic metrics to a content writing agent. The second agent can then draft social media posts tailored to the active audience.

You can use the `MCPServerHTTP` class from the framework's MCP module and apply a tool filter. This restricts a research agent to `get_trends_pages` while blocking them from real-time operational tools.

Yes, it is fully compatible with standard Python environments. You can run it locally over stdio or connect to our managed cloud endpoint using standard HTTP transports.

The server uses an isolated sandbox that handles all API requests ephemerally. Your campaign parameters and page view counts fetched via `get_trends_pages` are never cached or stored on our servers, maintaining strict data sovereignty.

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