How to Use the Geekflare MCP in CrewAI

Q: Can I have a CrewAI agent that only uses Geekflare's security tools?

Yes. When defining your agent, use the MCPServerHTTP class from crewai.mcp and provide a toolfilter function. This lets you expose only specific tools, like scanssltlscert and getdnsrecords, to that particular agent in your crew.

Q: What's the easiest way to get started with Geekflare and CrewAI?

The simplest method is to install crewaitools and pass the Geekflare MCP endpoint URL directly into the mcps list when you instantiate your Agent. CrewAI will automatically fetch and register all available tools for that agent.

Q: What data is exposed when my CrewAI agent uses the Geekflare MCP server to take a screenshot?

When an agent calls takewebsitescreenshot, the target URL is sent to the Geekflare service to perform the capture. The resulting screenshot image data is then streamed back to your agent. This interaction occurs within a secure, ephemeral Vinkius sandbox, and neither the URL nor the image is persisted after the task.

Deploy an autonomous DevOps crew with Geekflare and CrewAI. Let specialized agents monitor, diagnose, and report on your web infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geekflare MCP to CrewAI

Create your Vinkius account to connect Geekflare 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 Geekflare with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Site Reliability Crew

With CrewAI, you don't just run a script; you assemble a team. Create a "MonitorAgent" that periodically uses `measure_load_time` and `check_broken_links`. If it finds an issue, it passes the context and findings to a dedicated "DiagnosticsAgent". That DiagnosticsAgent can then dig deeper on its own. It might use `get_dns_records` to check for misconfigurations, `run_lighthouse_audit` to get a detailed performance breakdown, and `scan_ssl_tls_cert` to verify security. Each agent has a specific role, using Geekflare's tools to do its job.

Autonomous Security Audits

Build a security-focused crew that works around the clock. One agent, the "ReconAgent," could use `get_whois_data` to track domain ownership changes. A second agent, the "AuditAgent," can run `scan_ssl_tls_cert` across all your company's domains on a daily schedule. Then, a "ReportingAgent" takes the findings from the other agents and compiles a security brief. This entire workflow runs autonomously. The crew shares memory, so the ReportingAgent knows exactly what the other two found without you writing complex state-passing code.

Add Geekflare Tools to Your CrewAI Agents

Integrating this MCP server into CrewAI is simple. Just pass the Vinkius MCP endpoint URL to your Agent's `mcps` parameter. CrewAI handles the tool discovery, making all 7 Geekflare functions available to your agents to start working. For more control, you can use `MCPServerHTTP` and a `tool_filter` to assign specific tools to specific agents. This lets you enforce role specialization at the tool level. For example, your FrontendAgent gets `run_lighthouse_audit` and `take_website_screenshot`, while your SecurityAgent only gets `scan_ssl_tls_cert`.

Setup guide

Set up Geekflare 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 Geekflare tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Define two agents in your Crew. The first agent's task could be to run `check_broken_links` and pass its output to the second agent. The second agent's task would then be to take that list of broken links and investigate further, perhaps using `get_dns_records`.

Yes. When defining your agent, use the `MCPServerHTTP` class from `crewai.mcp` and provide a `tool_filter` function. This lets you expose only specific tools, like `scan_ssl_tls_cert` and `get_dns_records`, to that particular agent in your crew.

The simplest method is to install `crewai[tools]` and pass the Geekflare MCP endpoint URL directly into the `mcps` list when you instantiate your Agent. CrewAI will automatically fetch and register all available tools for that agent.

Yes, that's the whole point of using a crew. When one agent runs `run_lighthouse_audit`, the result becomes part of the shared context. Other agents in the crew can access that data to inform their own tasks without you needing to pass it around manually.

When an agent calls `take_website_screenshot`, the target URL is sent to the Geekflare service to perform the capture. The resulting screenshot image data is then streamed back to your agent. This interaction occurs within a secure, ephemeral Vinkius sandbox, and neither the URL nor the image is persisted after the 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