How to Use the Ocoya Social Media MCP in CrewAI

Q: How do I restrict which Ocoya Social Media tools a CrewAI agent can use?

Use the advanced MCPServerHTTP setup from crewai.mcp and apply a toolfilter. This lets you restrict access, ensuring an agent can run listautomations but cannot access sensitive user details via getme.

Deploy multi-agent teams to manage your Ocoya Social Media pipelines autonomously with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Ocoya Social Media MCP to CrewAI

Create your Vinkius account to connect Ocoya Social Media to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Ocoya Social Media with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Specialized agent squads for workspace auditing

This MCP Server lets you build a specialized agent squad to audit your active workspaces. CrewAI lets you build a team where a Researcher agent runs `list_workspaces` to map out the brand setup, while an Auditor agent uses `get_workspace` to inspect the details. These agents share memory, meaning the Auditor knows exactly which workspace to check without redundant API calls. This keeps your token usage low and your operations fast.

Collaborative post queue monitoring

This MCP Server allows a dedicated manager agent to coordinate your scheduled social queue. By exposing the tools to your crew, a monitoring agent can list active queues using `list_posts` while a supervisor agent decides which drafts need immediate attention. When a draft needs a deep dive, the supervisor agent tasks a writer agent with pulling the raw content via `get_post`. The crew works together to flag issues before they affect your audience.

Multi-agent profile tracking

This MCP Server lets your crew run parallel checks to track your social channels across departments. Your crew can run `list_profiles` to get a bird's-eye view of every connected channel across your entire business. If an agent detects an unverified channel, it tasks a specialist agent to fetch the metadata using `get_profile`. This automated delegation ensures your brand footprint is always accounted for without manual oversight.

Setup guide

Set up Ocoya Social Media 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 Ocoya Social Media tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Ocoya Social Media 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 Ocoya. 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 Ocoya Social Media 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 Ocoya Social Media MCP in CrewAI

You can pass the server URL directly into your agent's configuration using the `mcps` parameter. This instantly exposes tools like `list_posts` and `get_post` to that specific agent.

Yes. By configuring the server at the crew level or passing the URL to multiple agents, they can collaborate. One agent can run `list_profiles` while another uses the results to execute `get_profile`.

Use the advanced `MCPServerHTTP` setup from `crewai.mcp` and apply a `tool_filter`. This lets you restrict access, ensuring an agent can run `list_automations` but cannot access sensitive user details via `get_me`.

It supports stdio, SSE, and Streamable HTTP. You can choose the transport that matches your hosting environment.

All credentials and payloads containing your social profiles, posts, workspaces, and workflows are processed in memory within secure, ephemeral sandboxes. No data is stored, logged, or cached outside your local execution environment.

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