How to Use the Collibra MCP in Pydantic AI

Type-safe Collibra interactions for your Pydantic AI applications.

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 Pydantic AI

Create your Vinkius account to connect Collibra to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI agents creating Collibra assets

Define your asset models with Pydantic and let the agent populate Collibra. Using `create_asset`, the agent ensures your business records are always properly typed. If the response from the API doesn't match your schema, the agent catches it immediately. You avoid the headache of silent data corruption in your governance logs.

Searching Collibra data with Pydantic AI

Your agent can now fetch and validate asset details using `get_asset`. Every field is checked against your model before the agent proceeds. Use `search_assets` to find records and rely on Pydantic to parse the output. It turns raw API responses into structured, usable data objects for your logic.

Listing domains and communities in Pydantic AI

Retrieve your governance structure using `list_domains` and `list_communities`. The agent gets a clear picture of where assets live in your organization. By checking `list_asset_types` first, the agent ensures it only interacts with valid categories. It keeps your Pydantic AI agents operating within your predefined governance rules.

Setup guide

Set up Collibra MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "collibra-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Collibra tools.",
)

result = await agent.run("List recent Collibra transactions")
print(result.output)

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 Pydantic AI

Install the MCP toolset and register the HTTP endpoint. Your agent will treat the Collibra tools like any other type-safe function.

Yes. Every tool response is checked against your Pydantic models. If the API structure changes, your agent fails safely instead of using bad data.

It is fully supported. Just pass the MCPToolset to your agent and it handles the communication with your Vinkius server.

You must run the server externally. Pydantic AI connects to your Vinkius-hosted endpoint using SSE or HTTP.

The server transmits only the requested metadata fields. We use ephemeral, zero-trust tunnels to move this data, ensuring your internal governance details are never exposed.

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