4,500+ servers built on MCP Fusion
Vinkius
Ayuntamiento de Barcelona (CKAN) logo
Vinkius
OpenAI Agents SDK logo

How to Use the Ayuntamiento de Barcelona (CKAN) MCP in OpenAI Agents SDK

Build production agents that query Barcelona's public data using the OpenAI Agents SDK. Safe, traceable, and ready to deploy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Ayuntamiento de Barcelona (CKAN) MCP on Cursor AI Code Editor MCP Client Ayuntamiento de Barcelona (CKAN) MCP on Claude Desktop App MCP Integration Ayuntamiento de Barcelona (CKAN) MCP on OpenAI Agents SDK MCP Compatible Ayuntamiento de Barcelona (CKAN) MCP on Visual Studio Code MCP Extension Client Ayuntamiento de Barcelona (CKAN) MCP on GitHub Copilot AI Agent MCP Integration Ayuntamiento de Barcelona (CKAN) MCP on Google Gemini AI MCP Integration Ayuntamiento de Barcelona (CKAN) MCP on Lovable AI Development MCP Client Ayuntamiento de Barcelona (CKAN) MCP on Mistral AI Agents MCP Compatible Ayuntamiento de Barcelona (CKAN) MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect Ayuntamiento de Barcelona (CKAN) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Ayuntamiento de Barcelona (CKAN) to OpenAI Agents SDK 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

Run Validated SQL Queries

The `bcn_datastore_search_sql` tool lets your agent run raw SQL against Barcelona's open data resources. You can filter, join, and aggregate public records on urban planning or demographics directly from your agent. Because you're using the OpenAI Agents SDK, every query can be validated by built-in guardrails before it runs. This setup prevents malformed requests and gives you a full trace of your agent's actions in the OpenAI dashboard, which is critical for production systems.

Discover and Inspect Datasets

Your agent can start by listing all available datasets with `bcn_package_list` and then use `bcn_package_search` to find specific ones. Once a target is found, `bcn_package_show` pulls its complete metadata. This discovery process is perfect for multi-agent workflows. One agent can specialize in finding relevant data sources from the Ayuntamiento de Barcelona (CKAN) portal, then hand off the dataset's `resource_id` to another agent designed for SQL queries. The SDK handles the handoff and tool discovery automatically.

Connect Your OpenAI Agent to this MCP Server

Connecting this MCP Server to your agent is straightforward. You just instantiate the `MCPServerStreamableHttp` class with your Vinkius endpoint token and pass it to your Agent's constructor. Tool definitions are discovered automatically, so there's no manual schema mapping. For production, set `cacheToolsList=True` to avoid fetching the tool list on every startup. Your agent is now ready to query Barcelona's public data.

Setup guide

Set up Ayuntamiento de Barcelona (CKAN) MCP in OpenAI Agents SDK

Prerequisites

  • Python 3.10+ installed
  • openai-agents package (pip install openai-agents)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install the SDK

    Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.

  2. 2

    Connect via SSE transport

    Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Ayuntamiento de Barcelona (CKAN) tools at runtime.

  3. 3

    Create your Agent

    Pass the MCP to Agent(mcp_servers=[server]). The agent receives Ayuntamiento de Barcelona (CKAN) tools as native definitions — JSON schemas resolve automatically.

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Ayuntamiento de Barcelona (CKAN) tools and returns structured results. Copy the full example on the right to get started.

agent.py
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Ayuntamiento de Barcelona (CKAN) Agent",
            instructions="You have access to Ayuntamiento de Barcelona (CKAN) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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.

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 OpenAI Agents SDK

It happens automatically. When you pass the MCP server instance to your agent's constructor, the SDK calls the server to get a list of all available tools, like `bcn_package_search` and `bcn_datastore_search_sql`. No manual setup is needed.
Yes, but you'd handle this with your agent's system prompt and internal logic. The OpenAI Agents SDK itself is designed for automatic discovery, so you'd guide the agent's behavior through instructions rather than by filtering the tool list at the connection level.
Absolutely. The SDK has full tracing built-in. Every tool call your agent makes to this MCP Server, and the data it gets back, is logged and visible in your OpenAI dashboard.
The speed depends on the complexity of your query and the size of the dataset on Barcelona's CKAN portal. For best performance, use the `bcn_datastore_search` tool with specific filters to pull only the records you need, rather than downloading an entire resource.
Your queries about Barcelona's public datasets, urban records, and statistics are sent through Vinkius's ephemeral, zero-trust infrastructure. The connection is encrypted, and your Vinkius endpoint token authenticates the request without exposing your private keys.

Start using the Ayuntamiento de Barcelona (CKAN) MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 7 tools

We've already built the connector for Ayuntamiento de Barcelona (CKAN). Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 7 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.