How to Use the CountryStateCity MCP in AutoGen

Q: How do AutoGen agents share CountryStateCity tool outputs?

When an agent calls getcountry or liststates, the output is printed directly into the group chat context. Other agents in the AutoGen session can immediately read these ISO codes and geographic details to perform their own tasks. This ensures all agents work from the same verified geographic data.

Q: Can I limit which AutoGen agent can call CountryStateCity tools?

Yes, you can register the MCP tools to a specific AssistantAgent in your AutoGen group chat. For example, you can allow only your logistics agent to run listcitiesbystate, while other agents must ask it for geographic information.

Q: How does AutoGen handle errors from CountryStateCity tools?

If a tool like listcitiesbycountry fails due to tier restrictions, the error is returned to the calling AutoGen agent. The agent can then discuss the error with other agents and decide to switch to listcitiesbystate to complete the task.

Let your AutoGen agents debate and verify global geographic data using real-time ISO and regional lookups.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CountryStateCity MCP to AutoGen

Create your Vinkius account to connect CountryStateCity 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 CountryStateCity with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Consensus on Geographic Mapping

The CountryStateCity MCP Server delivers real-time geographic lookups to your AutoGen agent debates. When dealing with complex regional logistics, one agent can fetch country details with `get_country` while another verifies the state boundaries using `list_states`. The agents discuss the results in their chat session to resolve any naming conflicts or regional ambiguities before finalizing a delivery route. This collaborative approach prevents routing errors. By letting AutoGen agents cross-reference data from `list_cities_by_state`, you ensure your system reaches a consensus based on real geographic facts.

Secure Regional Verification in AutoGen Workflows

This regional data MCP Server allows your AutoGen agents to verify geographic boundaries collaboratively. Assign a dedicated security agent to monitor the geographic inputs used by your execution agents. While your primary agent gathers lists of regions using `list_countries`, the validator agent checks the returned ISO codes to verify they match your business rules. This division of labor keeps your workflows safe. You don't have to trust a single agent's execution when multiple AutoGen agents can double-check the geographic metadata.

AutoGen Tool Adaptation for Geographic Lookups

This geographic MCP Server integrates with AutoGen's schema adapter to expose regional lookups to your agents. AutoGen's tool adapter automatically translates the schema of tools like `get_state` into a format your conversational agents understand. Your agents can naturally request state-level details during their dialogue, calling the tools without any manual schema mapping on your part. Setting up this MCP Server with AutoGen requires just a few lines of code. Your conversational agents gain instant access to global geographic data, making their debates far more accurate.

Setup guide

Set up CountryStateCity 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 CountryStateCity 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="CountryStateCity_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CountryStateCity 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="CountryStateCity_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CountryStateCity 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 CountryStateCity. 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 CountryStateCity 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 CountryStateCity MCP in AutoGen

When an agent calls `get_country` or `list_states`, the output is printed directly into the group chat context. Other agents in the AutoGen session can immediately read these ISO codes and geographic details to perform their own tasks. This ensures all agents work from the same verified geographic data.

Yes, you can register the MCP tools to a specific `AssistantAgent` in your AutoGen group chat. For example, you can allow only your logistics agent to run `list_cities_by_state`, while other agents must ask it for geographic information.

If a tool like `list_cities_by_country` fails due to tier restrictions, the error is returned to the calling AutoGen agent. The agent can then discuss the error with other agents and decide to switch to `list_cities_by_state` to complete the task.

The AutoGen MCP extension supports both stdio and Streamable HTTP transports. When hosting on Vinkius, you will use the Streamable HTTP transport to connect your local agents to the managed server.

Absolutely. All geographic queries, ISO codes, and regional metadata are processed inside a zero-trust, isolated V8 sandbox. We do not store, log, or inspect the specific country or city data your agents query, keeping your operational logistics entirely private.

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