How to Use the Asian Development Bank MCP in AutoGen

Q: How do I configure the Asian Development Bank MCP Server in AutoGen?

Use StreamableHttpServerParams with your Vinkius endpoint URL. Pass the result into mcpservertools() to generate the tool list for your AssistantAgent.

Give your AutoGen multi-agent debates hard macroeconomic facts from the Asian Development Bank.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Asian Development Bank MCP to AutoGen

Create your Vinkius account to connect Asian Development Bank 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 Asian Development Bank with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject growth metrics into debates

The `get_gdp_asia` tool injects gross domestic product numbers into your agent conversations. An economic analyst agent pulls the growth metrics for IND and PRC, presenting the raw data to a strategy agent for review. They argue over the implications. The analyst points to the raw GDP figures fetched from the MCP Server, while a risk agent counters based on internal company data, forcing a consensus based on actual API responses rather than assumptions.

Challenge pricing strategies

The `get_inflation_asia` tool feeds consumer price data directly into your AutoGen negotiation loops. One agent requests the inflation rate for KOR or PHI, using that exact percentage to challenge another agent's regional pricing strategy. Setting this up requires minimal code. You pass the Vinkius URL to `mcp_server_tools()`, and the `McpToolAdapter` converts the schema automatically. Your AssistantAgent constructor ingests the tools and immediately knows how to query price stability.

Complex data for AutoGen MCP Server

The `query_adb_indicators` tool lets your setup pull complex trade and national account dataflows. Agents combine IDs like ADB,EO_BOP with economy codes to build a complete macroeconomic picture. Multiple agents parse this multi-dimensional data simultaneously. A quantitative agent crunches the NGDP_XDC numbers while a qualitative agent writes a summary, debating the final output until both agree the data supports the conclusion.

Setup guide

Set up Asian Development Bank 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 Asian Development Bank 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="Asian Development Bank_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Asian Development Bank 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="Asian Development Bank_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Asian Development Bank 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 Asian Development 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 Asian Development Bank 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 Asian Development Bank MCP in AutoGen

Use `StreamableHttpServerParams` with your Vinkius endpoint URL. Pass the result into `mcp_server_tools()` to generate the tool list for your AssistantAgent.

Yes. You assign the tool list to specific agents in your group chat. An execution agent makes the API calls while other agents analyze the results.

The schema defines exact parameters like JPN, KOR, and VIE. If an agent tries an invalid code, the error message becomes part of the conversation, prompting a correction.

No. AutoGen handles schema conversion natively through its MCP adapter. The agent understands the required dataflow IDs without manual prompt engineering.

Completely. The Vinkius endpoint executes in an isolated V8 sandbox. Your agents request public CPI and GDP indicators, and your internal negotiation transcripts remain strictly local.

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