How to Use the Urlbox MCP in CrewAI

Q: Can CrewAI use Urlbox for automated reporting?

Yes, you can make the final step of your crew call generatepdf. This ensures that after all the agents have researched and analyzed a URL, the result is automatically compiled into a professional PDF.

Run automated web content checks using Urlbox with CrewAI's agent teamwork.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Urlbox MCP to CrewAI

Create your Vinkius account to connect Urlbox 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 Urlbox with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate PDF reports from the whole page.

The `generate_pdf` tool lets a dedicated reporting agent compile all gathered information into one final, clean document. This is ideal when multiple agents have finished their analysis and need to pass a single output. You simply feed the URL, and the MCP Server takes care of rendering it into a PDF that CrewAI can then use for its final deliverable.

Capture base visual evidence.

Use `take_screenshot` when an agent needs basic proof of concept. It grabs a standard PNG image, providing quick visual context to the whole crew for analysis. This simple capture is perfect for passing raw data between specialized agents that need immediate input.

Get full page context for research.

The `take_full_page_screenshot` tool provides a comprehensive visual base for the whole crew. One agent can grab this, and another can analyze it for structural issues. It gives the necessary context—the 'big picture' view—that specialized agents need to collaborate on complex tasks.

Setup guide

Set up Urlbox 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 Urlbox tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the MCP Server endpoint directly into your agent setup. This lets different roles—like a 'Researcher' and an 'Auditor'—access the same set of tools to work on one goal.

Yes, you can make the final step of your crew call `generate_pdf`. This ensures that after all the agents have researched and analyzed a URL, the result is automatically compiled into a professional PDF.

It provides multiple levels of visual evidence: basic screenshots, high-resolution retina shots, or full page captures. Your crew can select the right tool based on whether deep fidelity or broad context is needed.

The MCP Server handles rendering various web pages and formats, allowing your agents to operate on everything from simple static text sites to complex single-page applications.

This server processes the visual and textual metadata of external URLs. It generates PNG, PDF, and other image formats derived from those web pages.

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