How to Use the ECB Discovery — Universal Statistical Data Access MCP in LangChain

Q: Can I trace ECB Discovery — Universal Statistical Data Access tool calls using LangSmith?

Yes, every execution of queryecbdata or listdataflows is fully visible in your LangSmith dashboard. You see the exact payload, latency, and token cost of each ECB query.

Feed real-time European Central Bank data directly into your LangChain pipelines without writing custom API wrappers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ECB Discovery — Universal Statistical Data Access MCP to LangChain

Create your Vinkius account to connect ECB Discovery — Universal Statistical Data Access 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 ECB Discovery — Universal Statistical Data Access with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover ECB dataflows inside LangChain agents

The `list_dataflows` tool lists every active database code and description directly inside your agentic run. Your agent reads this catalog, identifies the correct dataset, and passes it straight to the next node in your graph. This MCP setup lets your chain dynamically scan the European Central Bank database, find the right statistical codes, and feed them forward without hardcoding a single endpoint.

Run multi-step SDMX queries with this MCP Server

Your agent uses `query_ecb_data` to pull raw statistics once it identifies the target series key. By chaining this tool immediately after a catalog search, your pipeline fetches raw exchange rates or yield curves on the fly. The output flows directly into your next LLM prompt or processing chain. You watch the entire sequence execute inside LangSmith, tracking exactly how the agent resolved the SDMX key before pulling the numbers.

Build autonomous macroeconomic research chains

This MCP server exposes raw financial feeds directly to your ReAct agents. The agent evaluates intermediate data from `query_ecb_data` and decides whether to fetch more history or switch to a different dataflow entirely. You get a self-correcting loop for European economic data. If a query returns empty, the agent backtracks, checks `list_dataflows` for a better match, and tries again without crashing your run.

Setup guide

Set up ECB Discovery — Universal Statistical Data Access 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 ECB Discovery — Universal Statistical Data Access 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({
    "ecb-discovery-universal-statistical-data-access-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 ECB Discovery — Universal Statistical Data Access 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 European Central Bank. 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 ECB Discovery — Universal Statistical Data Access 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 ECB Discovery — Universal Statistical Data Access MCP in LangChain

Install langchain-mcp-adapters and run the MultiServerMCPClient pointing to our hosted endpoint. Call client.get_tools() to load the tools directly into your agent constructor.

Yes, every execution of `query_ecb_data` or `list_dataflows` is fully visible in your LangSmith dashboard. You see the exact payload, latency, and token cost of each ECB query.

Your LLM agent processes the user prompt, looks up the dataflow code via `list_dataflows`, and constructs the correct SDMX key. It then feeds that key directly into `query_ecb_data` in a single, continuous chain.

No. The tools return clean, parsed JSON data directly to your agent. Your chains read the structured output immediately without any extra parsing steps.

No. We run a zero-trust V8 sandbox that processes your queries ephemerally. Your request payload and the retrieved ECB exchange or interest rate data never persist on our servers using this secure MCP setup.

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