How to Use the Curator.io MCP in CrewAI

Q: How do I pass Curator.io tools to multiple CrewAI agents?

You can configure the Vinkius URL in the mcps list when defining your agents. This gives every agent in your crew access to the entire toolset, allowing them to collaborate on feed management tasks.

Q: Can CrewAI agents collaborate on debugging Curator.io connection issues?

Yes, one agent can run listsocialconnections to find broken accounts, while another uses getaccountdetails to verify if you have exceeded your Curator.io API limits.

Q: Can I limit which tools my CrewAI agents can access?

Yes, you can apply a toolfilter to only expose read-only tools like listfeedposts to your research agents, keeping configuration tools restricted to your admin agent.

Deploy a specialized team of autonomous CrewAI agents to monitor, moderate, and optimize your Curator.io feeds.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Curator.io MCP to CrewAI

Create your Vinkius account to connect Curator.io 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 Curator.io with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Social Media Crews with this MCP Server

Invoking `list_active_feeds` lets your Auditor Agent check feed health while a separate Moderator Agent handles content filtering. CrewAI lets you deploy a team of specialized agents that work together to manage your brand's online presence. These agents share memory and context, allowing them to pass critical data seamlessly. For example, when the Auditor Agent finds an active feed, the Moderator Agent immediately uses `list_moderation_rules` to verify its safety parameters.

Autonomous Ingestion Monitoring in CrewAI

Calling `list_feed_sources` allows a dedicated Ingestion Agent to map out every connected account and hashtag source. Your agents can run continuous sweeps across all external platforms using this MCP Server to ensure your content pipeline is healthy. If a source stops feeding content, the agent queries `get_feed_post_count` to measure the drop-off. It then passes this data to an Escalation Agent, who can notify your marketing team with specific details about the broken connection.

Autonomous Post Moderation and Search

Using `search_posts_in_feed` allows a Curation Agent to flag posts containing specific brand keywords or sensitive topics. Instead of manually reviewing thousands of social posts, you can let your crew handle the heavy lifting. Once flagged, the agent passes these posts to a Reviewer Agent that cross-references them with results from `list_feed_posts`. This collaborative approach ensures that only high-quality, relevant content makes it to your public-facing widgets.

Setup guide

Set up Curator.io 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 Curator.io tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can configure the Vinkius URL in the `mcps` list when defining your agents. This gives every agent in your crew access to the entire toolset, allowing them to collaborate on feed management tasks.

Yes, one agent can run `list_social_connections` to find broken accounts, while another uses `get_account_details` to verify if you have exceeded your Curator.io API limits.

The framework supports standard SSE and HTTP MCP transports. You can use the MCPServerHTTP class from crewai.mcp to connect your crew.

Yes, you can apply a `tool_filter` to only expose read-only tools like `list_feed_posts` to your research agents, keeping configuration tools restricted to your admin agent.

Vinkius runs the integration inside an ephemeral V8 sandbox that wipes all session data immediately after your crew finishes its tasks. Your API credentials and social media feeds are never exposed to external networks or stored on disk.

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