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

Q: How do I register the ECB Discovery — Universal Statistical Data Access server in AutoGen?

Install autogen-extmcp and use the mcpservertools helper to load the tools from our endpoint. Pass the resulting tool list directly to your AssistantAgent constructor.

Q: Can multiple AutoGen agents access ECB Discovery — Universal Statistical Data Access simultaneously?

Yes, all agents in your group chat can share access to queryecbdata and listdataflows. The adapter handles schema conversion so any agent can call the tools during a debate.

Q: How do AutoGen agents negotiate SDMX keys using ECB Discovery — Universal Statistical Data Access MCP Server?

One agent searches the catalog using listdataflows and proposes a key structure. The other agents review the code, suggest corrections, and only execute queryecbdata once they reach a consensus.

Let your AutoGen agents debate and analyze live European Central Bank statistics using direct SDMX database queries.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve complex macroeconomic debates in AutoGen

The `list_dataflows` tool gives your analyst agents instant access to the entire ECB database catalog. One agent can locate the proper dataflow code while another agent challenges the selection based on historical relevance. This MCP flow ensures your agents don't query the wrong datasets. They discuss the available options, agree on the best statistical code, and pass it to the execution agent.

Execute multi-agent consensus checks with this MCP Server

The `query_ecb_data` tool fetches the raw series data once your agents agree on the target keys. A data verification agent can run the query, while a critic agent reviews the output for anomalies or unexpected trends. You get a self-correcting statistical pipeline. If the critic agent flags a discrepancy in the exchange rates, the group can automatically trigger a new query with a revised SDMX key.

Coordinate automated economic research groups

This MCP server provides the raw financial tools your conversational agents need to build complete reports. By combining `list_dataflows` and `query_ecb_data`, your agents run independent tasks, compare results, and synthesize a single consensus document. The framework handles the coordination. You simply set the goal, and your agents use the server to pull the numbers and debate the economic implications in their group chat.

Setup guide

Set up ECB Discovery — Universal Statistical Data Access MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes ECB Discovery — Universal Statistical Data Access tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="ECB Discovery — Universal Statistical Data Access_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ECB Discovery — Universal Statistical Data Access data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="ECB Discovery — Universal Statistical Data Access_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ECB Discovery — Universal Statistical Data Access data")
    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 AutoGen

Install autogen-ext[mcp] and use the mcp_server_tools helper to load the tools from our endpoint. Pass the resulting tool list directly to your AssistantAgent constructor.

Yes, all agents in your group chat can share access to `query_ecb_data` and `list_dataflows`. The adapter handles schema conversion so any agent can call the tools during a debate.

One agent searches the catalog using `list_dataflows` and proposes a key structure. The other agents review the code, suggest corrections, and only execute `query_ecb_data` once they reach a consensus.

Yes, the adapter supports both transport protocols. You can connect to our hosted HTTP endpoint or run the server locally via stdio depending on your pipeline architecture.

Your ECB financial data never leaves the secure, ephemeral V8 sandbox of this MCP setup. We handle all authentication tokens on our end, ensuring your queries for interest rates and monetary aggregates are processed securely without being stored.

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