How to Use the Collibra MCP in LangChain

Q: Can I trace Collibra tool calls from LangChain in LangSmith?

Yes, every call to tools like searchassets or getasset shows up in your LangSmith dashboard. You see the exact payload, latency, and token usage for each run.

Run multi-step data governance chains in LangChain with direct access to Collibra data catalogs.

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 LangChain

Create your Vinkius account to connect Collibra to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Multi-Step Governance Chains

This MCP server exposes `list_domains` and `create_asset` directly to your LangChain agent so you can build self-correcting data governance pipelines. Your agent queries existing domains, verifies the layout, and writes new assets without manual intervention. You trace every tool execution in LangSmith to monitor latency and token costs during complex runs. If a tool call fails, your chain catches the error and tries a different branch automatically.

Validate Assets with LangChain Agents

The `get_asset` and `list_statuses` tools let your LangChain agent inspect data quality metrics and approval states. The agent pulls the asset details and compares them against your internal compliance rules. You can feed these outputs into other chain links, like sending a slack alert or updating a database. The entire decision loop runs within your python runtime, giving you full control over the execution flow.

Search and Map Communities via MCP Server

The `search_assets` and `get_community_details` tools give your LangChain chains the ability to look up data owners across your entire organization. Your agent finds the right asset and immediately resolves who owns the parent community. This setup lets you build automated data discovery tools that run inside your LangGraph workflows using the MCP adapter. You combine Collibra metadata with your local vector databases to find missing documentation fast.

Setup guide

Set up Collibra MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Collibra tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "collibra-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Collibra transactions"
    })
    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 LangChain

You initialize the MCP adapter in your python code and pass the tools directly to your agent. The agent calls `list_assets` and other endpoints to make decisions during execution.

Yes, every call to tools like `search_assets` or `get_asset` shows up in your LangSmith dashboard. You see the exact payload, latency, and token usage for each run.

Vinkius manages the credentials and gives you a single endpoint token. You pass this token to your MCP client setup, keeping your Collibra API keys out of your application code.

Your LangChain agent handles the API error through standard exception handling. You can configure retry logic or fallback chains to handle rate limits or missing assets.

Your data catalog metadata, including asset names, domain layouts, and community details, runs through a zero-trust V8 sandbox. Vinkius never stores your Collibra API payloads.

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