How to Use the Dades Obertes Catalunya MCP in LlamaIndex

Q: How do I expose Dades Obertes Catalunya tools to LlamaIndex?

Install llama-index-tools-mcp and set up a BasicMCPClient. Call await mcptoolspec.totoollistasync() and hand those tools to your FunctionAgent.

Q: How do I restrict which datasets my agent accesses?

Use the allowedtools filter in your setup. You restrict the agent to specific pre-defined searches so it doesn't wander through unrelated government archives.

Index Catalonia's open data directly into your LlamaIndex knowledge base using this MCP connection for grounded semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dades Obertes Catalunya MCP to LlamaIndex

Create your Vinkius account to connect Dades Obertes Catalunya 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 Dades Obertes Catalunya with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Public Catalonian Data

RAG applications fail when they lack current civic information. You point `search_catalog` at the portal to locate relevant demographic or financial datasets. The resulting IDs tell your setup exactly where to pull the raw information. Your agent grabs the metadata and prepares it for ingestion into your vector store.

Filter via LlamaIndex MCP Server

You don't want to embed an entire unindexed government database. The `query_dataset` tool applies SoQL `$limit` and `$where` clauses to slice the data before it ever hits your embedding model. This targeted extraction keeps your chunks highly relevant. Your semantic search now surfaces exact funding amounts or transit schedules instead of guessing.

Ground Answers in Real Records

Hallucinations destroy trust in analytical tools. By integrating these specific civic endpoints, your query engine references actual API responses from the regional government. Users ask plain English questions about regional statistics. The system retrieves the exact municipal rows from your index and synthesizes a perfectly accurate answer.

Setup guide

Set up Dades Obertes Catalunya 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 Dades Obertes Catalunya 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 Dades Obertes Catalunya tools.",
)
response = await agent.run("List recent Dades Obertes Catalunya 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 Dades Obertes Catalunya. 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 Dades Obertes Catalunya 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 Dades Obertes Catalunya MCP in LlamaIndex

Install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Call `await mcp_tool_spec.to_tool_list_async()` and hand those tools to your `FunctionAgent`.

That is the exact use case. Your agent pulls specific rows using the query tool and immediately indexes them into a searchable vector store for later retrieval.

Not at all. The LLM translates your natural language prompt into the correct `$select` and `$where` syntax before hitting the public API.

Use the `allowed_tools` filter in your setup. You restrict the agent to specific pre-defined searches so it doesn't wander through unrelated government archives.

You are pulling public civic budgets and transit schedules. The Vinkius endpoint operates on a zero-trust model, ensuring your embedding prompts never leak into the public API layer.

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