How to Use the Gobierno Abierto Valencia MCP in LangChain

Q: How do I connect the Gobierno Abierto Valencia MCP Server to LangChain?

Install the adapter with pip install langchain-mcp-adapters langgraph. Use MultiServerMCPClient to connect to the MCP Server URL, call gettools(), and pass them to your LangChain agent.

Q: Can a LangChain agent query specific table rows from the Gobierno Abierto Valencia portal?

Yes, by chaining tools together. Your agent uses showresource to find the right resource ID, then calls searchdatastore to run target queries on that specific municipal dataset.

Q: How does LangSmith help debug Gobierno Abierto Valencia tools in LangChain?

LangSmith logs every single tool call like listpackages or showpackage. You can inspect the exact payload returned from Valencia's servers to see why a chain failed or how many tokens the raw data consumed.

Q: What happens if Valencia's API returns a massive dataset?

You should instruct your agent to use searchdatastore with specific filters instead of pulling the entire resource. This keeps the token payload small and prevents your chains from hitting context limits.

Feed real-time Valencia municipal data directly into your LangChain decision chains and ReAct agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gobierno Abierto Valencia MCP to LangChain

Create your Vinkius account to connect Gobierno Abierto Valencia to LangChain 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 Gobierno Abierto Valencia with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map municipal datasets inside LangChain chains

The `list_groups` tool lets your agent fetch the broad categories of public data available on the Valencia portal. Your agent takes these categories and passes them to the next link in your LangChain pipeline, narrowing down the scope before running deeper queries. Instead of guessing, your chain uses the output of `list_packages` to find the exact dataset name. This keeps your multi-step pipelines running with real-world identifiers instead of hardcoded assumptions.

Inspect specific package metadata on the fly

The `show_package` tool retrieves complete metadata for any target dataset your chain identifies. LangChain agents use this structural information to understand the schema and fields before attempting to pull actual records. This metadata step prevents your agent from making blind guesses about the data format. By feeding this schema directly into your model context, you avoid parser errors and keep your LangSmith traces clean.

Run direct datastore queries via MCP Server tools

The `search_datastore` tool queries the actual records inside a specific Valencia data resource. Your LangChain agent can filter, sort, and extract specific municipal statistics to answer complex user prompts on demand. Combining this with `show_resource` allows your chain to verify the file format and structure before running the query. You get a direct pipeline from Valencia's public registry straight into your conversational agent's context.

Setup guide

Set up Gobierno Abierto Valencia MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Gobierno Abierto Valencia tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "gobierno-abierto-valencia-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Gobierno Abierto Valencia transactions"
    })
    print(result["messages"][-1].content)

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 Gobierno Abierto Valencia. 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 Gobierno Abierto Valencia 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 Gobierno Abierto Valencia MCP in LangChain

Install the adapter with `pip install langchain-mcp-adapters langgraph`. Use `MultiServerMCPClient` to connect to the MCP Server URL, call `get_tools()`, and pass them to your LangChain agent.

Yes, by chaining tools together. Your agent uses `show_resource` to find the right resource ID, then calls `search_datastore` to run target queries on that specific municipal dataset.

LangSmith logs every single tool call like `list_packages` or `show_package`. You can inspect the exact payload returned from Valencia's servers to see why a chain failed or how many tokens the raw data consumed.

You should instruct your agent to use `search_datastore` with specific filters instead of pulling the entire resource. This keeps the token payload small and prevents your chains from hitting context limits.

This server only touches public municipal data and records from Valencia's open portal, so no private user data is sent. The connection runs through Vinkius's isolated MCP sandbox, ensuring your internal pipeline configuration and API tokens remain completely 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