How to Use the Asian Development Bank MCP in Pydantic AI

Q: How does Pydantic AI connect to the Asian Development Bank MCP Server?

Initialize an MCPToolset with your Vinkius HTTP URL. Passing this array to your Agent constructor lets the framework handle the rest.

Enforce strict runtime validation on Asia-Pacific economic data using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Asian Development Bank to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Asian Development Bank MCP Server integration

Raw macroeconomic dataflows like ADB,EO_NA for GDP come from the `query_adb_indicators` tool. Pydantic AI validates every single field returned by the Vinkius endpoint against your predefined schemas. Catching bad data before it corrupts your downstream financial models is critical. If the API sends a string instead of a float for a metric, the framework throws a validation error immediately.

Extract validated GDP metrics

Requesting gross domestic product figures happens via `get_gdp_asia`. Agents ask for specific economy codes such as PRC, JPN, IND, and KOR. Using the unified `MCPToolset` class connects the external server over HTTP. Dropping the deprecated MCPServerHTTP approach gives you a cleaner, type-checked integration.

Track consumer price inflation

CPI data for markets like INO, THA, VIE, and PHI arrives through `get_inflation_asia`. Models from OpenAI, Anthropic, or local providers interact with this tool exactly the same way. Failing loudly is the entire point here. Hallucinated country codes or missing fields trigger exceptions, forcing the agent to retry the tool call with correct parameters.

Setup guide

Set up Asian Development Bank MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "asian-development-bank-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Asian Development Bank tools.",
)

result = await agent.run("List recent Asian Development Bank transactions")
print(result.output)

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 Pydantic AI

Initialize an `MCPToolset` with your Vinkius HTTP URL. Passing this array to your Agent constructor lets the framework handle the rest.

Runtime checks happen on every response. Unexpected formats for GDP or inflation numbers cause the system to raise a strict validation error.

Local execution works flawlessly. Being completely model-agnostic means running Llama locally interacts with the external tools just as well as cloud providers.

Join the indicator codes with a plus symbol. Fetching multiple metrics like NGDP_XDC+PCPI_PCH happens in one go.

Single endpoint tokens handle the authentication layer on Vinkius. Queries for trade and population figures run inside an ephemeral sandbox that shuts down the millisecond your data finishes transferring.

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