How to Use the Junta de Andalucía (Portal) MCP in CrewAI

Q: How do I add the Junta de Andalucía (Portal) tools to a CrewAI agent?

Add the MCP Server's HTTP endpoint to your agent's mcps list during initialization. The agent automatically discovers tools like getpackage and searchdatastore and uses them based on its assigned role.

Q: Can a CrewAI agent search for specific file formats in the Junta de Andalucía (Portal)?

Yes. The agent uses getresource to inspect the metadata of specific files, identifying whether they are CSVs, PDFs, or APIs before deciding how to parse them.

Q: Is it possible to filter portal data by category in CrewAI?

Yes. Your researcher agent can call listgroups to understand the portal's classification system, allowing it to target only relevant categories like health or education.

Deploy specialized agent crews to analyze, cross-reference, and report on Andalusian public records using CrewAI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Junta de Andalucía (Portal) MCP to CrewAI

Create your Vinkius account to connect Junta de Andalucía (Portal) to CrewAI 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 Junta de Andalucía (Portal) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate regional research to specialized crews

The `list_packages` tool allows a researcher agent to scan the entire catalog of Andalusian public datasets. In a CrewAI setup, this agent finds the relevant package names and hands them off to an analyst agent for deeper inspection. This separation of labor keeps your agents focused. The researcher doesn't waste execution context analyzing files; it simply builds the list of targets and passes them along the chain.

Query portal databases autonomously

The `search_datastore` tool enables an analyst agent to run targeted queries on live database tables hosted by the regional government. Your CrewAI team uses this tool to extract specific rows of interest without downloading gigabytes of raw files. The analyst agent runs the query, extracts the relevant statistics, and writes a summary. A writer agent then takes that summary to draft reports, all without human intervention.

Map government agencies using this MCP Server

The `list_organizations` tool provides your crew with a structured list of all public departments publishing data in Andalusia. A coordinator agent can use this tool to categorize datasets by their originating department before assigning analysis tasks to other agents. This ensures your crew understands the administrative structure of the data they are processing. It prevents agents from misattributing public records to the wrong regional department.

Setup guide

Set up Junta de Andalucía (Portal) MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Junta de Andalucía (Portal) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Junta de Andalucía (Portal) Analyst",
    goal="Access and analyze Junta de Andalucía (Portal) data via MCP.",
    backstory="Expert analyst with direct Junta de Andalucía (Portal) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Junta de Andalucía (Portal) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Junta de Andalucía (Portal) Analyst",
        goal="Access and analyze Junta de Andalucía (Portal) data via MCP.",
        backstory="Expert analyst with direct Junta de Andalucía (Portal) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Junta de Andalucía (Portal) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 Junta de Andalucía. 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 Junta de Andalucía (Portal) 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 Junta de Andalucía (Portal) MCP in CrewAI

Add the MCP Server's HTTP endpoint to your agent's `mcps` list during initialization. The agent automatically discovers tools like `get_package` and `search_datastore` and uses them based on its assigned role.

Yes. The agent uses `get_resource` to inspect the metadata of specific files, identifying whether they are CSVs, PDFs, or APIs before deciding how to parse them.

CrewAI agents use shared memory to pass dataset metadata, such as package IDs retrieved from `list_packages`, from one specialized agent to another during a task run.

Yes. Your researcher agent can call `list_groups` to understand the portal's classification system, allowing it to target only relevant categories like health or education.

The server communicates exclusively with the public open data endpoints of the Andalusian government. Your private agent prompts, API keys, and internal crew communications never touch the public registry.

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