How to Use the Collibra MCP in CrewAI

Q: How do I restrict a CrewAI agent from using specific Collibra MCP tools?

You use the MCPServerHTTP class to filter tools. This allows you to expose only read tools like listassets to your research agents while keeping write tools locked down.

Deploy specialized CrewAI agent teams to autonomously audit your Collibra data assets using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Collibra MCP to CrewAI

Create your Vinkius account to connect Collibra 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 Collibra with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent Collibra audits with CrewAI

Divide and conquer your data catalog chores. Assign one agent to run `search_assets` to find undocumented entries, while another uses `get_asset` to analyze their metadata. Because this MCP Server supports shared memory, the agents pass context seamlessly. They work together to flag missing information without you writing a single line of glue code.

Autonomous community and domain mapping

Let a specialized mapping crew organize your workspace. One agent queries `list_communities` and `list_domains` to understand your current catalog hierarchy. A second agent uses `get_community_details` and `list_domain_types` to find where assets are misaligned, preparing a clean report of where files actually belong.

Automated asset creation and status tracking

Speed up your data onboarding. An ingestion agent can identify new files, check their status with `list_statuses`, and then run `create_asset` to register them. A supervisor agent monitors the entire run, ensuring that every asset type matches the allowed schemas returned by `list_asset_types` before committing.

Setup guide

Set up Collibra 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 Collibra tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You simply pass your Vinkius HTTP endpoint URL into the agent's `mcps` array parameter. The framework automatically parses the available tools and makes them accessible to that specific agent.

Yes, your agents can share access to the toolset. One can search using `search_assets` while another updates statuses, executing tasks in parallel or sequentially.

You use the `MCPServerHTTP` class to filter tools. This allows you to expose only read tools like `list_assets` to your research agents while keeping write tools locked down.

It supports stdio, SSE, and Streamable HTTP. Vinkius manages the hosting, so you can connect your framework using whichever method fits your deployment architecture.

Absolutely. All communication is encrypted in transit and runs within an isolated, zero-trust environment. Your community details and asset schemas are never cached or logged by the proxy.

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