How to Use the CNMC (Comisión Mercados y Competencia) MCP in LangChain

Q: How do I pass CNMC (Comisión Mercados y Competencia) data between steps in LangChain?

You use the output of packagesearch to feed the resource ID directly into datastoresearch within a single chain. LangChain agents handle this transition by parsing the JSON response and passing the parameters to the next tool call automatically.

Q: How does LangChain handle connection errors with the CNMC (Comisión Mercados y Competencia) server?

The MultiServerMCPClient manages the HTTP connection and raises standard exceptions if the Spanish portal is unreachable. Your chain can catch these exceptions to retry the search or fall back to cached market data.

Feed Spanish market data straight into your LangChain runs to build autonomous, multi-step regulatory analysis loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CNMC (Comisión Mercados y Competencia) MCP to LangChain

Create your Vinkius account to connect CNMC (Comisión Mercados y Competencia) 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 CNMC (Comisión Mercados y Competencia) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain CNMC catalog lookups directly into your LangChain agents

The `package_search` tool lets your agent query the Spanish open data registry to locate specific market competition datasets using the MCP standard. LangChain handles this by feeding the search results directly into the next step of your chain, removing the need for manual ID copying. You track the entire execution path using LangSmith, giving you a clear view of how the agent selected the dataset. This transparency helps you debug why a specific competition file was pulled during a run.

Extract raw market metrics for sequential analysis

The `datastore_search` tool pulls raw rows from CNMC resources using the ID resolved in your previous chain step. LangChain feeds this tabular regulatory data straight into your downstream prompts for analysis. Because the connection details remain hidden, your agent focuses entirely on parsing the Spanish market data. You get clean JSON payloads representing real-time competition figures directly inside your active chain context.

Build multi-step regulatory pipelines with LangGraph

This MCP server plugs directly into your LangGraph setup using the `MultiServerMCPClient` class to coordinate multi-step research. Your graph determines when to pull market data and when to branch off into calculations. State management remains clean as the agent moves from searching the CNMC catalog to extracting specific competition records. You control the flow while LangChain traces every single tool call for auditability.

Setup guide

Set up CNMC (Comisión Mercados y Competencia) 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 CNMC (Comisión Mercados y Competencia) 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({
    "cnmc-comision-mercados-y-competencia-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 CNMC (Comisión Mercados y Competencia) 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 CNMC (Comisión Mercados y Competencia). 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 CNMC (Comisión Mercados y Competencia) 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 CNMC (Comisión Mercados y Competencia) MCP in LangChain

You use the output of `package_search` to feed the resource ID directly into `datastore_search` within a single chain. LangChain agents handle this transition by parsing the JSON response and passing the parameters to the next tool call automatically.

Yes, every call to the Spanish market registry appears in LangSmith with full input and output payloads. You can inspect the exact query parameters used for finding competition datasets and see the raw records returned.

The `MultiServerMCPClient` manages the HTTP connection and raises standard exceptions if the Spanish portal is unreachable. Your chain can catch these exceptions to retry the search or fall back to cached market data.

No, LangChain inspects the MCP server endpoint and registers the schemas for you. Your agents instantly know how to format queries for Spanish competition and market datasets without custom wrapper code.

All requests run through Vinkius's sandboxed V8 isolates, meaning your MCP server access tokens never leak to the public Spanish portal. Only the specific query parameters you send to find datasets leave the secure runtime environment.

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