How to Use the World Bank Countries MCP in AutoGen

Q: If I need regional validation for World Bank Countries using AutoGen?

You run agents that query searchregions. One agent might push for the largest possible region, while another insists on a smaller, more specific classification. The final output is their negotiated decision.

Q: What metadata types does World Bank Countries support in AutoGen's debate?

It supports discrete data points: country codes from listcountries, income levels from searchincomelevels, and geographic regions from searchregions. These are the inputs for agent deliberation.

Get consensus on World Bank Countries metadata using the AutoGen multi-agent CONVERSATION framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect World Bank Countries MCP to AutoGen

Create your Vinkius account to connect World Bank Countries 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 World Bank Countries with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating country lists and regions

You can set up multiple agents to debate data validity. One agent calls `list_countries` while another uses `search_regions`. They then negotiate which metadata structure best fits the ultimate goal. This consensus-driven approach is ideal when your answer requires more than a simple API call; it demands deliberation between competing perspectives.

Assessing income risks among agents

A security agent can use `search_income_levels` to flag specific classifications (like 'LIC') while a performance agent checks the available regions via `search_regions`. They debate which combination represents the highest risk profile. The resulting decision is not just data; it's a negotiated conclusion based on multiple, conflicting metadata inputs.

Multi-perspective metadata querying

You can deploy agents to query different facets simultaneously. For example, one agent checks if the country is listed in `list_countries`, while another verifies its regional placement using `search_regions`. The system doesn't just return two lists; it reaches a single, validated conclusion that satisfies all criteria provided by the World Bank Countries metadata.

Setup guide

Set up World Bank Countries 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 World Bank Countries 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="World Bank Countries_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent World Bank Countries 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="World Bank Countries_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent World Bank Countries 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 World Bank Open Data. 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 World Bank Countries 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 World Bank Countries MCP in AutoGen

It facilitates consensus-driven decision making. Instead of just returning a list, your agents debate which combination of country codes, regions, and income levels is most accurate for the specific scenario.

The framework handles lists of countries, global income classifications (HIC/LIC), and geographic region data. Agents use these distinct inputs to challenge each other's assumptions.

You run agents that query `search_regions`. One agent might push for the largest possible region, while another insists on a smaller, more specific classification. The final output is their negotiated decision.

It supports discrete data points: country codes from `list_countries`, income levels from `search_income_levels`, and geographic regions from `search_regions`. These are the inputs for agent deliberation.

This server touches structured metadata: country ISO codes, geographic regions, and global income/lending classifications. Because these tools deal only in public classification standards, the system never handles private user information.

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