How to Use the Ayuntamiento de Barcelona (CKAN) MCP in Google ADK

Q: How do I add the Ayuntamiento de Barcelona (CKAN) tools to my agent in Google ADK?

You wrap the server in an McpToolset and pass it to your LlmAgent's tools parameter. Google ADK handles the rest. You can also use the toolnames filter on the McpToolset if you only want to expose certain tools, like bcndatastoresearch.

Q: What's the difference between bcndatastoresearch and bcndatastoresearchsql?

bcndatastoresearch performs a simple keyword search with filters, which is fast and easy. bcndatastoresearchsql lets you run a full SQL query, which is more powerful for aggregations or complex joins but requires you to know the data structure.

Connect Gemini agents to Barcelona's city data with Google ADK. Analyze public datasets alongside your own BigQuery tables.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ayuntamiento de Barcelona (CKAN) MCP to Google ADK

Create your Vinkius account to connect Ayuntamiento de Barcelona (CKAN) to Google ADK 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 Ayuntamiento de Barcelona (CKAN) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Public Data with SQL

Give your Gemini agent the ability to query Barcelona's open data portal directly using SQL. The `bcn_datastore_search_sql` tool executes SQL against specific dataset resources, letting your agent perform complex analysis on demand. This is powerful when combined with Google ADK's native integrations. Your agent can pull public environmental data from Barcelona, then cross-reference it with your private logistics data stored in BigQuery, all within a single agentic workflow.

Search and Find Specific Datasets

Your agent doesn't need to know dataset IDs in advance. It can use `bcn_package_search` to find datasets related to a topic, like 'bicicletas' or 'calidad del aire', and then use `bcn_package_show` to inspect the metadata and find the right resource to query. Because Google ADK is built for Gemini's long-context models, the agent can hold the details of multiple datasets in its context. This allows it to compare data sources and decide which one is best for answering a user's question about the city.

Integrate with Your Google Cloud Agent

Adding these tools to your agent is simple. You create an `McpToolset` instance pointing to your Vinkius server URL and include it in the `tools` list when initializing your `LlmAgent`. This MCP Server fits right into your existing Google Cloud environment. You can run your agent on Vertex AI, trigger it with Cloud Functions, and manage its entire lifecycle using familiar Google Cloud tools and infrastructure.

Setup guide

Set up Ayuntamiento de Barcelona (CKAN) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Ayuntamiento de Barcelona (CKAN) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Ayuntamiento de Barcelona (CKAN)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Ayuntamiento de Barcelona (CKAN) tools via MCP.",
    tools=mcp_tools,
)

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 Open Data BCN. 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 Ayuntamiento de Barcelona (CKAN) 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 Ayuntamiento de Barcelona (CKAN) MCP in Google ADK

You wrap the server in an `McpToolset` and pass it to your `LlmAgent`'s `tools` parameter. Google ADK handles the rest. You can also use the `tool_names` filter on the `McpToolset` if you only want to expose certain tools, like `bcn_datastore_search`.

Yes, that's a primary use case. Your agent can query the Barcelona MCP Server for public statistics, then use its native Google Cloud tools to query your private BigQuery tables and reason over the combined results.

No, it works with any Gemini model supported by Google ADK. However, using a model with a large context window is a good idea, as it allows the agent to better analyze the detailed metadata and data returned by tools like `bcn_current_packages`.

`bcn_datastore_search` performs a simple keyword search with filters, which is fast and easy. `bcn_datastore_search_sql` lets you run a full SQL query, which is more powerful for aggregations or complex joins but requires you to know the data structure.

All requests concerning Barcelona's public datasets and statistics are routed through the Vinkius platform. Each request is handled in a sandboxed, ephemeral environment, and your connection is secured end-to-end. Your authentication is managed by a single token, not direct credentials.

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