How to Use the ArcXP MCP in CrewAI

Q: How do I prevent a rogue CrewAI agent from deleting all my ArcXP content?

You control which tools each agent has. Only grant the deleteanscontent tool to a specific, trusted agent. You can also use CrewAI's process controls to ensure that agent only runs under supervision or with explicit approval.

Deploy a crew of specialized AI agents to autonomously manage your ArcXP newsroom 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 ArcXP MCP to CrewAI

Create your Vinkius account to connect ArcXP 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 ArcXP with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Autonomous Content Team

Assign specific roles to different agents to create a fully autonomous newsroom crew. A 'Researcher' agent can use `search_ans_content` to find source material. A 'Copy Editor' agent can then be tasked with using `update_ans_content` to fix typos and grammar. This isn't just one agent doing everything. CrewAI lets you build a team where each member has a specific job and a limited set of tools. They collaborate by passing work to each other, just like a human team.

Automate Content Auditing and Moderation

You can build a crew to monitor your content. An 'Auditor' agent could run on a schedule, using `get_ans_content` to check articles for compliance. If it finds a problem, it passes the job to a 'Moderator' agent. That Moderator agent could have a different set of tools. For minor issues, it might use `update_ans_content` to add a warning label. For major violations, you could give it access to the `delete_ans_content` tool to remove the article entirely.

Build a Full Newsroom Crew with CrewAI

Model your entire publishing process with a multi-agent system. A 'Reporter' agent can file new stories using `create_ans_content`. It then passes the story ID to an 'Editor' agent, who reviews the work and uses `update_ans_content` to publish it. A 'Photo Desk' agent can listen for new articles and use `search_photo_assets` to find and attach relevant images. With this MCP server, you have all the tools you need to build a self-running operation on top of ArcXP.

Setup guide

Set up ArcXP 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 ArcXP tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Yes, that's a perfect use case. You can assign a 'Photo Agent' the `search_photo_assets` tool and a 'Video Agent' the `get_video_asset` tool. A third 'Archivist' agent could then coordinate their work to build galleries or collections.

You control which tools each agent has. Only grant the `delete_ans_content` tool to a specific, trusted agent. You can also use CrewAI's process controls to ensure that agent only runs under supervision or with explicit approval.

That's the core principle of CrewAI. The first agent executes its task, like using `search_ans_content`, and its findings are passed to the next agent in the crew. That second agent then uses those results to perform its own task, like calling `update_ans_content`.

It's straightforward. In your agent's definition, you just include the Vinkius MCP server URL in the `mcps` list. CrewAI handles the connection and makes the tools available to that agent automatically.

Your agents' access is limited to the ArcXP content data they request, such as ANS payloads and author information. The Vinkius MCP server isolates each tool call in its own secure sandbox. Your CrewAI setup only needs the server URL, not direct credentials, which keeps your secrets safe.

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