How to Use the COR MCP in CrewAI

Q: Can I restrict which COR tools a CrewAI agent can access?

Yes, you can use the MCPServerHTTP class with a toolfilter to limit access. This ensures your research agent can only read tasks while your manager agent can create them.

Q: How do I check the current user's role in CrewAI?

Your agent can call getcorme to read the authenticated profile details. This helps the agent determine if it has the necessary permissions to perform administrative actions.

Run autonomous multi-agent crews to manage COR projects and balance team workloads using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect COR MCP to CrewAI

Create your Vinkius account to connect COR 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 COR with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent agency operations

The `list_cor_tasks` tool feeds raw project data into a specialized crew of collaborative agents. One agent analyzes current tasks for delays, while a second agent uses `list_cor_team_members` to find the right person to unblock the work. This collaborative execution happens entirely in the background. Your agents pass context to each other, resolving resource bottlenecks without manual intervention.

Autonomous margin and budget monitoring

The `list_cor_projects` tool gives your financial monitoring crew the high-level metrics they need to track profit margins. A supervisor agent monitors these numbers and tasks an analyst agent with investigating any project that drops below profit targets. The analyst then queries `list_cor_time_entries` to pinpoint exactly where hours were overspent. The crew compiles a detailed report of the leak and presents it to your management team.

Automated client onboarding via MCP Server

The `list_cor_clients` tool allows your client-facing agents to map out existing customer profiles before setting up new work. When a new contract is signed, a specialized agent triggers `create_cor_project` to build the workspace. Another agent immediately populates the project with standard milestones using `list_cor_task_types`. This ensures every new client gets a consistent, rapid onboarding experience.

Setup guide

Set up COR 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 COR tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass your Vinkius endpoint URL directly into the agent's mcps configuration array. CrewAI handles the MCP connection and exposes the tools to that specific agent.

Yes, you can use the MCPServerHTTP class with a tool_filter to limit access. This ensures your research agent can only read tasks while your manager agent can create them.

Agents share a memory space, allowing an analysis agent to pass a specific project ID found via list_cor_projects to an execution agent that updates tasks via our secure MCP layer.

Your agent can call `get_cor_me` to read the authenticated profile details. This helps the agent determine if it has the necessary permissions to perform administrative actions.

All tool execution runs within an ephemeral V8 sandbox, ensuring your client lists and task records are never cached. Vinkius acts as a secure, pass-through gateway with zero persistent storage.

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