How to Use the Collibra MCP in LlamaIndex

Q: How does Collibra connect to LlamaIndex?

You use the MCP tool spec to load tools like searchassets directly into your LlamaIndex agent. This lets the agent query your data catalog during active retrieval steps.

Q: Can I run semantic search on Collibra assets in LlamaIndex?

Yes, you can index the output of listassets into a vector store. This allows LlamaIndex to perform semantic search over your metadata instead of relying on exact keyword matches.

Q: How does this MCP server prevent hallucination in LlamaIndex?

The agent pulls fresh metadata directly using getasset during the query cycle. Grounding the generation step in live API data ensures the output matches your actual Collibra setup.

Q: How do I filter Collibra domains within LlamaIndex?

You configure the agent to call listdomains with specific parameters. LlamaIndex filters the tool outputs before indexing them, so you only ingest the business domains you care about.

Index your Collibra data catalog into LlamaIndex vector stores for grounded, hallucination-free retrieval.

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 LlamaIndex

Create your Vinkius account to connect Collibra to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG Pipelines on Collibra Assets

The `list_assets` and `get_asset` tools feed your LlamaIndex pipelines with real-time data catalog metadata. Your agent queries these tools to pull live schemas and definitions, bypassing static document files. The retrieved data is indexed into your vector store for semantic search. This prevents your agent from hallucinating asset details, as every response is grounded in actual Collibra records.

Semantic Search over Collibra Domains via MCP Server

This MCP server exposes `list_domains` and `list_domain_types` to let LlamaIndex map out your data governance structure. The agent indexes these domains to understand how different business units organize their data. When users ask questions about data ownership, the agent queries the index to find the correct domain. This turns complex governance structures into easily searchable knowledge graphs.

Index Governance Statuses and Communities

The `list_statuses` and `list_communities` tools provide the necessary governance context for your LlamaIndex knowledge base. Your agent checks the status of assets before serving them to users. This ensures that your RAG application only references approved assets. You control which lifecycle stages are searchable, keeping deprecated or draft data out of user-facing answers.

Setup guide

Set up Collibra MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Collibra MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Collibra tools.",
)
response = await agent.run("List recent Collibra data")

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 LlamaIndex

You use the MCP tool spec to load tools like `search_assets` directly into your LlamaIndex agent. This lets the agent query your data catalog during active retrieval steps.

Yes, you can index the output of `list_assets` into a vector store. This allows LlamaIndex to perform semantic search over your metadata instead of relying on exact keyword matches.

The agent pulls fresh metadata directly using `get_asset` during the query cycle. Grounding the generation step in live API data ensures the output matches your actual Collibra setup.

You configure the agent to call `list_domains` with specific parameters. LlamaIndex filters the tool outputs before indexing them, so you only ingest the business domains you care about.

Yes, your asset names, descriptions, and community structures remain private. Vinkius executes the tool calls inside isolated sandboxes, and your API keys never leave the secure environment.

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