How to Use the Geoapify MCP in AutoGen

Q: How do I register Geoapify tools in my AutoGen setup?

Use mcpservertools with a StreamableHttpServerParams pointing to your endpoint. The McpToolAdapter automatically converts the JSON schemas so you can pass the tool list directly to your AssistantAgent constructor.

Q: How do AutoGen agents handle Geoapify API errors during a debate?

If calculateisoline fails due to invalid parameters, the error returns as a standard tool message. The agent reads the error, adjusts the time or distance constraints, and retries the tool call automatically.

Give your AutoGen multi-agent systems the ability to debate and optimize complex spatial logistics using Geoapify.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geoapify MCP to AutoGen

Create your Vinkius account to connect Geoapify 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 Geoapify with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent logistics with Geoapify MCP Server

Logistics optimization requires competing priorities. You configure one AutoGen agent to minimize fuel costs using `route_planner`, while a second customer service agent argues for faster delivery times. They debate the outputs, adjusting constraints until they reach a consensus. When the agents disagree on a specific path, they call `calculate_route` for different transit modes. The cost agent checks the truck route, while the speed agent checks the standard drive route. The final negotiated path balances both operational metrics perfectly.

Verify spatial data through agent consensus

Raw GPS traces from field devices are often messy. A data ingestion agent pulls the raw tracks and runs them through `map_matching` to snap the coordinates to the actual road network. A quality assurance agent then reviews the snapped geometry. If the track looks suspicious, the QA agent cross-references the data by calling `get_elevation`. It checks if the altitude changes match the known terrain. The agents converse about the discrepancies before approving the final spatial record.

Coordinate bulk geocoding tasks

Processing thousands of legacy addresses requires architectural coordination. A manager agent chunks the dataset and calls `create_batch_job` to handle the bulk geocoding. It then assigns a worker agent to monitor the job status. The worker agent periodically calls `get_batch_job`. Once the coordinates return, a third validation agent runs `geocode_reverse` on a random sample to verify accuracy. The system manages the entire asynchronous workflow through natural agent dialogue.

Setup guide

Set up Geoapify 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 Geoapify 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="Geoapify_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your endpoint. The `McpToolAdapter` automatically converts the JSON schemas so you can pass the tool list directly to your `AssistantAgent` constructor.

Yes. You initialize the Vinkius MCP client once and pass the resulting tool list to any agent that needs spatial capabilities. They share the same underlying HTTP transport.

If `calculate_isoline` fails due to invalid parameters, the error returns as a standard tool message. The agent reads the error, adjusts the time or distance constraints, and retries the tool call automatically.

Definitely. You give the routing tools to your logistics agent and the `search_places` tool to your research agent. This forces them to communicate and trade information to solve complex geospatial problems.

The Vinkius MCP server operates on a zero-trust model. When your agent sends raw GPS tracks to `map_matching`, the data processes in a temporary isolate environment that drops all state the millisecond the snapped route returns to your client.

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