How to Use the Collibra MCP in AutoGen

Q: Can multiple AutoGen agents access Collibra simultaneously?

Yes, multiple agents can call getasset or listassets during a single conversation turn. The framework coordinates the tool execution and shares the results across the chat.

Coordinate multi-agent debates in AutoGen to validate and register Collibra assets automatically.

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 AutoGen

Create your Vinkius account to connect Collibra to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Consensus for Collibra Assets

The `create_asset` and `list_statuses` tools allow your AutoGen agents to collaborate on registering new data assets. A data steward agent proposes an asset, while a compliance agent reviews its status before writing to Collibra. The agents debate the completeness of the metadata in their chat history. Once they reach consensus, the designated writer agent executes the tool call to publish the asset.

Automated Domain Audits via AutoGen MCP Server

This MCP server exposes `list_domains` and `list_domain_types` to let your AutoGen group chats audit your catalog structure. One agent pulls the list of domains, and another checks them against organization policies. If a domain violates naming conventions, the agents negotiate the required fixes. They draft a report and assign tasks to correct the records without user intervention.

Resolve Ownership Conflicts with AutoGen

The `get_community_details` and `list_communities` tools give your AutoGen agents the context needed to resolve data ownership. When a new asset is orphaned, the agents discuss which community fits best. They compare the asset's tags against existing community profiles. The agents agree on the best owner, then update the metadata using the appropriate API calls.

Setup guide

Set up Collibra MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Collibra tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Collibra_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Collibra data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Collibra_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Collibra data")
    print(result.messages[-1].content)

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 AutoGen

You register the tools using the AutoGen MCP adapter. This makes tools like `search_assets` available to all agents in your group chat, allowing them to query the catalog during their debate.

Yes, multiple agents can call `get_asset` or `list_assets` during a single conversation turn. The framework coordinates the tool execution and shares the results across the chat.

When agents disagree on an asset status, they use the tool outputs to debate. They query `list_statuses` to find valid states and negotiate until they reach a consensus.

You connect via the Vinkius endpoint using your single token. The adapter handles the schema conversion, so your AutoGen agents see the tools as native python functions.

Your metadata, including asset schemas and community structures, is processed in ephemeral V8 sandboxes. Vinkius ensures that no sensitive Collibra credentials or payloads are logged.

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