Bring Spain
to OpenAI Agents SDK
Learn how to connect CNMC (Comisión Mercados y Competencia) to OpenAI Agents SDK and start using 2 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
Compatible with every major AI agent and IDE
What is the CNMC (Comisión Mercados y Competencia) MCP Server?
Connect to the official Open Data portal of the CNMC (Comisión Nacional de los Mercados y la Competencia). This server allows AI agents to explore and extract public data regarding telecommunications, energy, transport, and postal sectors in Spain.
What you can do
- Catalog Discovery — Use
package_searchto find datasets, resources, and metadata using keywords or specific queries. - Data Extraction — Use
datastore_searchto pull actual records and rows from specific resources using their unique IDs. - Granular Filtering — Apply JSON filters to narrow down results to specific dates, regions, or categories within a dataset.
- Resource Inspection — Identify update frequencies, license types, and resource formats before processing data.
How it works
- Subscribe to this server
- Enter your CNMC API Key (if required for higher rate limits)
- Start querying Spanish market data from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Data Analysts — quickly fetch market statistics without manual CSV downloads
- Legal & Compliance Teams — monitor regulatory data and competition records
- Policy Researchers — access public sector information for economic modeling and reporting
Built-in capabilities (2)
g., a CSV file within a dataset). Requires a resource_id obtained via package_search. Retrieve actual records from a specific CNMC resource
Use this to find the resource_id needed for datastore_search. Search for datasets and resources in the CNMC catalog
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 2 tools from CNMC (Comisión Mercados y Competencia) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries CNMC (Comisión Mercados y Competencia), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
CNMC (Comisión Mercados y Competencia) in OpenAI Agents SDK
CNMC (Comisión Mercados y Competencia) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect CNMC (Comisión Mercados y Competencia) to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for CNMC (Comisión Mercados y Competencia) in OpenAI Agents SDK
The CNMC (Comisión Mercados y Competencia) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 2 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
CNMC (Comisión Mercados y Competencia) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the CNMC (Comisión Mercados y Competencia) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Cocktail API
8 toolsSearch cocktail recipes — audit ingredients and instructions via AI.

Mailingwork
10 toolsExecute professional email marketing campaigns with advanced segmentation, A/B testing, and GDPR-compliant list management.

vCard Contacts Parser
1 toolsInstantly convert massive iPhone and Android `.vcf` contact exports into structured JSON. Turn your AI into a hyper-intelligent local address book.

SMOTE Oversampling Engine
1 toolsBalance skewed datasets instantly by generating mathematically sound synthetic minority data points via KNN.
