How to Use the Nominatim MCP in AutoGen

Q: How do AutoGen agents coordinate when calling Nominatim tools?

One AutoGen agent can call search to find a location, while another agent uses getdetails to verify its parent administrative hierarchy. They pass the resulting Nominatim OSM IDs back and forth in their conversational loop to reach a consensus.

Q: How do I register Nominatim tools with my AutoGen assistant using MCP?

Use the AutoGen MCP extension to load the tools into your AssistantAgent. The schema conversion happens automatically, allowing your agents to invoke search or lookuposm directly during their discussions.

Q: What happens if the Nominatim coordinate lookup returns multiple results in AutoGen?

The search tool returns a list of matching places sorted by importance, which your AutoGen agent can inspect. The agent checks the bounding boxes and selects the most relevant result based on the conversation context.

Enable multi-agent geographic consensus and address validation in your AutoGen workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nominatim MCP to AutoGen

Create your Vinkius account to connect Nominatim 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 Nominatim with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent location validation using this MCP Server

The `search` tool allows your AutoGen planning agent to look up coordinates for a list of delivery destinations. A separate AutoGen validation agent then takes those coordinates and runs `reverse_geocode` to verify that the address matches the intended postal code. If the two agents find a mismatch in the spatial data, they debate the discrepancy. This collaborative check prevents incorrect coordinates from being written to your routing database.

Deep spatial inspection for AutoGen routing agents

The `get_details` tool provides your AutoGen agents with the full administrative hierarchy and importance score of a specific place. Your routing agent uses this data to decide if a location is a major transit hub or a minor residential street. When planning complex routes, the AutoGen agent uses `lookup_osm` to fetch the exact boundaries of commercial zones. Having access to these detailed boundaries helps the AutoGen agents coordinate drop-off points more accurately.

Monitor geocoding service health during AutoGen debates

The `get_status` tool lets your AutoGen coordinator agent check if the MCP service is responding quickly before assigning tasks to the mapping agents. If latency is high, the coordinator instructs the team to throttle their spatial queries. Because AutoGen agents talk to each other in real-time, checking the Nominatim status prevents the group from hitting rate limits. The agents automatically space out their calls to `search` to stay under the one-request-per-second limit.

Setup guide

Set up Nominatim 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 Nominatim 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="Nominatim_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One AutoGen agent can call `search` to find a location, while another agent uses `get_details` to verify its parent administrative hierarchy. They pass the resulting Nominatim OSM IDs back and forth in their conversational loop to reach a consensus.

Yes, if two AutoGen agents disagree on a location, they can run `reverse_geocode` on the coordinates to get the exact address details. Comparing the structured address components helps the agents resolve the conflict programmatically.

Use the AutoGen MCP extension to load the tools into your `AssistantAgent`. The schema conversion happens automatically, allowing your agents to invoke `search` or `lookup_osm` directly during their discussions.

The `search` tool returns a list of matching places sorted by importance, which your AutoGen agent can inspect. The agent checks the bounding boxes and selects the most relevant result based on the conversation context.

Yes, all address lookups and coordinate queries executed by AutoGen are isolated in a zero-trust runtime. The spatial data is transmitted securely to OpenStreetMap, and no location records are saved or shared with external parties.

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