CNMC MCP for AI. Pull Spanish Market Data Directly Into Your Agent.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
CNMC (Comisión Nacional de los Mercados y la Competencia) provides direct access to Spanish public market data. Use this MCP to search, filter, and retrieve official records across major sectors like energy, telecommunications, transport, and postal services.
It lets your agent pull structured statistics directly from the CNMC open data portal without manual CSV downloads.
What your AI can do
Datastore search
Retrieves actual records from a specific CNMC resource ID that you already found.
Package search
Searches the entire CNMC catalog using keywords to find relevant datasets and resources.
Search the CNMC catalog using general keywords or queries to find relevant data packages.
Narrow down large datasets, pulling only rows matching specific dates, regions, or categories.
Retrieve actual structured data records from a specified resource ID.
Ask an AI about this
Waiting for input…
CNMC (Comisión Mercados y Competencia) MCP - 2 Tools
These two tools let you find the right datasets and pull structured records from the CNMC open data portal using your agent.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using CNMC (Comisión Mercados y Competencia) on VinkiusDatastore Search
Retrieves actual records from a specific CNMC resource ID that you already found.
Package Search
Searches the entire CNMC catalog using keywords to find relevant datasets and...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with CNMC (Comisión Mercados y Competencia), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 2 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Collecting Spanish Market Data used to be a massive manual chore.
Before using this connector, you had to jump between the CNMC website and various specialized portals. You’d manually search for 'energy' data, find the correct resource link, download a multi-gigabyte CSV file, open it in Excel, and then write formulas just to filter down to the specific quarter or region you actually needed.
Now, your agent handles that entire sequence. You ask for what you need—a filtered record set from a specific sector. It runs `package_search` behind the scenes to find the resource ID, uses that ID in `datastore_search`, and returns only the clean, relevant data table right away.
Using the CNMC MCP gives you direct access to filtered records.
The two main manual steps that disappear are searching for the resource ID and then running complex filters within a spreadsheet. You don't copy, paste, or manually check dates anymore.
You simply ask your agent for the data you want, specifying the parameters, and it executes the full sequence of finding and retrieving. It’s that simple.
What your AI can actually do with this
Need market stats for Spain? This connector gives your AI client direct access to the CNMC's public data catalog. You can stop spending hours navigating government websites or downloading massive, disorganized spreadsheets. Instead, you tell your agent what you need—like 'total natural gas consumption in 2022'—and it handles the complex search logic itself.
The MCP lets your agent perform two critical steps: first, it finds the specific dataset ID using keywords; second, it pulls only the exact records and rows you requested from that resource. This means whether you're running competitive analysis or writing a regulatory report, you get clean, filtered data right back to your chat window.
It’s built into Vinkius, so once you connect your agent, you gain access to this specific Spanish market data alongside thousands of others. You just point it at the problem, and it pulls the numbers.
019e387a-5179-724b-a248-40c2e7dc489e Here's how it actually works
The bottom line is: your agent handles the multi-step workflow—discovery, filtering, and extraction—in one go.
First, use package_search to look through the CNMC catalog. You provide keywords (e.g., 'energy sector') and get back potential datasets and their unique IDs.
Second, identify the specific resource ID you need. Then, your agent uses this ID with datastore_search to pull the actual records from that data source.
Finally, if needed, apply JSON filters during the search process. This limits the results so you only get data for a specific region or year.
Who is this actually for?
This MCP targets policy researchers, legal compliance teams, and data analysts. It’s for anyone who needs clean, verifiable market statistics from Spanish public records without spending half their day clicking through government portals.
Accessing official sector information for economic modeling or writing policy papers on energy and transport.
Monitoring regulatory changes and competition records to ensure adherence to Spanish market laws.
Quickly fetching, filtering, and compiling comparative market statistics across different sectors for client reports.
What Changes When You Connect
Stop manual CSV downloads. Instead of clicking through multiple government portals, the package_search tool finds all relevant datasets using simple keywords.
Get granular control over your data. You can apply JSON filters to narrow down results by date or region when you use datastore_search, keeping your output clean and focused.
Cover key Spanish sectors easily. The MCP handles market statistics for telecommunications, energy, transport, and postal services—all in one place.
Save time on data discovery. You don't have to know the exact resource ID; package_search helps you find that initial dataset link first.
Process structured records instantly. The agent pulls raw rows directly into your chat interface, ready for immediate analysis.
See it in action
Comparing energy consumption across years
A researcher needs to compare natural gas usage from 2019 vs. 2022. Instead of downloading two massive files, they ask the agent to search for 'natural gas' using package_search, get the resource ID, and then use datastore_search with a filter for both years in one query.
Checking telecom market share changes
A compliance analyst needs to track how market shares changed across regions. They prompt the agent, asking it to find 'telecom' datasets and apply JSON filters specifically for region codes (e.g., Madrid) and Q2 records.
Building a report on transport trends
A data analyst wants general stats on rail travel. They use package_search to locate the primary 'transport' dataset, then execute datastore_search to pull only the records related to passenger volume and specific years.
The honest tradeoffs
Trying to search raw data without an ID
Asking the agent simply to 'show me energy stats.' The agent can't find anything because it needs a unique resource identifier.
First, run package_search with keywords like 'energy sector.' This returns the necessary resource IDs. Then, use those specific IDs in datastore_search to get the data.
Ignoring filters on large datasets
Retrieving all records for a dataset when you only needed Q1 2023 data. This results in too much noise and extra work.
Always apply JSON filters as part of your request to datastore_search. Specify the exact date range, region, or category upfront.
When It Fits, When It Doesn't
Use this MCP if your core need is pulling structured, public sector statistical data from Spanish government sources (telecom, energy, transport). It's ideal for compliance checks and historical modeling. Don't use it if you are looking for unstructured documents, real-time operational APIs (like checking a single meter reading), or proprietary internal company records—those require different types of connections. If your data needs to be validated against a specific schema before usage, look into validation tools; this MCP focuses purely on retrieval.
Questions you might have
How do I find the resource_id needed for data retrieval? +
Use the package_search tool with a query related to your topic. The response will include a list of resources, each with a unique id (the resource_id) that you can then use in datastore_search.
Can I limit the number of records returned to avoid large payloads? +
Yes! The datastore_search tool includes an optional limit parameter. You can specify exactly how many rows you want to retrieve (e.g., 10 or 100) to keep the response concise.
Is it possible to filter data by a specific field, like a year or a city? +
Absolutely. Use the filters parameter in datastore_search. It accepts a JSON string (e.g., {"Year": "2023"}) to return only the records that match your criteria.
When running `datastore_search`, do I need to manage my rate limits or API credentials? +
Yes, while initial queries are fine, sustained high-volume retrieval requires an API key. Your agent must use this key for datastore_search to maintain consistent access and prevent throttling errors.
If I run `datastore_search` and get an error, should I first re-run `package_search`? +
Absolutely. If the data retrieval fails, the issue is often with the resource ID. Use package_search again to verify that you have the correct, current unique identifier for your target dataset.
Does `package_search` allow me to look up datasets outside of telecommunications or energy sectors? +
The catalog covers multiple domains within Spanish market regulation. Use package_search with broader keywords to locate resources related to transport, postal services, and other relevant economic areas.
What is the expected format when I successfully execute a query using `datastore_search`? +
The data retrieved from datastore_search comes in structured records. Your agent will process these rows, making them ready for immediate analysis or further filtering within your client environment.
What is the proper workflow when using `package_search` before attempting any data pulls? +
The first step must always be to run package_search. This locates the specific dataset and provides the required unique resource ID, which you then feed into datastore_search for actual records.
We've already built the connector for CNMC. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 2 tools are live and waiting.
You're up and running in seconds.
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.
Built, hosted, and secured by Vinkius. You just connect and go.