SDMX (Statistical Data and Metadata eXchange) is an international standard for exchanging statistical data. The ECB, Eurostat, IMF, World Bank, and other institutions use SDMX for their APIs. Data is organized in dataflows → dimensions → observations.

Do I need an API key to access this data?

No, the ECB Statistical Data Warehouse public API is completely open and free. There is no authentication or token required to fetch any of the datasets provided.

How often is the statistical data updated?

The data is updated in real-time according to the ECB's official publishing schedule. Daily exchange rates typically update around 16:00 CET.

ECB Discovery — Universal Statistical Data Access MCP Server for Pydantic AI 2 tools — connect in under 2 minutes

Name: ECB Discovery — Universal Statistical Data Access
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 2 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect ECB Discovery — Universal Statistical Data Access through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to ECB Discovery — Universal Statistical Data Access "
            "(2 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in ECB Discovery — Universal Statistical Data Access?"
    )
    print(result.data)

asyncio.run(main())

ECB Discovery — Universal Statistical Data Access

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About ECB Discovery — Universal Statistical Data Access MCP Server

Universal access to all ECB data.

Pydantic AI validates every ECB Discovery — Universal Statistical Data Access tool response against typed schemas, catching data inconsistencies at build time. Connect 2 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

2 Tools

List Dataflows — Complete catalog of ECB datasets
Query Data — Any dataflow with custom SDMX keys

The ECB Discovery — Universal Statistical Data Access MCP Server exposes 2 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect ECB Discovery — Universal Statistical Data Access to Pydantic AI via MCP

Follow these steps to integrate the ECB Discovery — Universal Statistical Data Access MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 2 tools from ECB Discovery — Universal Statistical Data Access with type-safe schemas

Why Use Pydantic AI with the ECB Discovery — Universal Statistical Data Access MCP Server

Pydantic AI provides unique advantages when paired with ECB Discovery — Universal Statistical Data Access through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your ECB Discovery — Universal Statistical Data Access integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your ECB Discovery — Universal Statistical Data Access connection logic from agent behavior for testable, maintainable code

ECB Discovery — Universal Statistical Data Access + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the ECB Discovery — Universal Statistical Data Access MCP Server delivers measurable value.

Type-safe data pipelines: query ECB Discovery — Universal Statistical Data Access with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple ECB Discovery — Universal Statistical Data Access tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query ECB Discovery — Universal Statistical Data Access and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock ECB Discovery — Universal Statistical Data Access responses and write comprehensive agent tests

ECB Discovery — Universal Statistical Data Access MCP Tools for Pydantic AI (2)

These 2 tools become available when you connect ECB Discovery — Universal Statistical Data Access to Pydantic AI via MCP:

list_dataflows

Each dataflow has a code (e.g., EXR, FM, BSI) and description. Use these codes with the generic query tool to access any ECB data. List all available ECB statistical dataflows

query_ecb_data

Provide the dataflow code (EXR, FM, BSI, YC, MIR, BKN, etc.) and a SDMX series key. Use list_dataflows to find dataflow codes. Example: dataflow=EXR, key=D.USD.EUR.SP00.A for daily USD/EUR rate. Query any ECB dataset with a SDMX series key — universal access

Example Prompts for ECB Discovery — Universal Statistical Data Access in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with ECB Discovery — Universal Statistical Data Access immediately.

"What ECB datasets are available?"

"Query the Balance Sheet Items (BSI) dataset."

"Extract the latest MFI Interest Rates."

Troubleshooting ECB Discovery — Universal Statistical Data Access MCP Server with Pydantic AI

Common issues when connecting ECB Discovery — Universal Statistical Data Access to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

ECB Discovery — Universal Statistical Data Access + Pydantic AI FAQ

Common questions about integrating ECB Discovery — Universal Statistical Data Access MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your ECB Discovery — Universal Statistical Data Access MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.