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

Q: How do I add Junta de Andalucía (Portal) tools to LlamaIndex?

Run pip install llama-index-tools-mcp. Create a BasicMCPClient, wrap it in an McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Can a LlamaIndex agent query specific files in the Junta de Andalucía (Portal)?

The agent uses the searchdatastore tool to look inside supported dataset resources. It extracts the raw data and indexes the results for immediate querying.

Q: Can I limit which MCP Server tools the agent uses?

You can restrict the agent's access using the allowedtools filter. This prevents it from running broad searches if you only want it checking specific packages.

Q: How do I get LlamaIndex to read the actual Junta de Andalucía (Portal) data?

Set includeresources=True when configuring the tool spec. This permits the framework to ingest the payload returned by the Andalusian API.

Index Andalusian public records into searchable vector stores using LlamaIndex 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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Andalusian Datasets

The `list_packages` tool grabs the full catalog of available datasets from the Andalusian portal so your LlamaIndex application can build a complete semantic map. Instead of asking an LLM to guess what public data exists, you ground its knowledge in the actual, live directory. It calls `get_package` to ingest the metadata for each entry. Your RAG pipeline turns those descriptions into embeddings. When a user asks about regional agriculture statistics, the system retrieves the exact package ID from the vector store. It stops hallucinations cold by forcing the agent to cite real government sources.

RAG with Government Resources

Executing `get_resource` pulls the specific file metadata you need to fetch raw Andalusian records. Your LlamaIndex setup can then use `search_datastore` to extract the actual rows of data. It pulls these facts straight into the index. You are building a system that answers questions using live government APIs. The agent queries the MCP Server, receives the structured JSON response, and synthesizes an answer based strictly on those retrieved rows.

Map Organizational Knowledge

Using `list_organizations` alongside `list_groups` allows your ingestion engine to categorize every piece of data by its source department. LlamaIndex reads this hierarchy and builds document nodes that retain their original government context. Users can filter their semantic searches by specific departments. If someone only wants data from the Ministry of Health, the index restricts its retrieval to that organization's namespace. It makes massive public catalogs highly targeted.

Setup guide

Set up Junta de Andalucía (Portal) 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 Junta de Andalucía (Portal) 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 Junta de Andalucía (Portal) tools.",
)
response = await agent.run("List recent Junta de Andalucía (Portal) 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 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 LlamaIndex

Run `pip install llama-index-tools-mcp`. Create a `BasicMCPClient`, wrap it in an `McpToolSpec`, and pass the async tool list to your `FunctionAgent`.

The agent uses the `search_datastore` tool to look inside supported dataset resources. It extracts the raw data and indexes the results for immediate querying.

You can restrict the agent's access using the `allowed_tools` filter. This prevents it from running broad searches if you only want it checking specific packages.

Set `include_resources=True` when configuring the tool spec. This permits the framework to ingest the payload returned by the Andalusian API.

The isolated V8 sandbox processes your requests for open metadata without logging the contents. Data flows directly into your local vector store, keeping your indexing operation entirely private.

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