How to Use the Jawg Maps (Location & Routing) MCP in AutoGen

Q: How do I add Jawg Maps (Location & Routing) to my AutoGen setup?

Install the extension with pip install -U "autogen-extmcp". Use mcpservertools pointing to your Vinkius MCP endpoint, and pass the resulting tools list straight to your AssistantAgent constructor.

Q: Can AutoGen agents resolve addresses using Jawg Maps (Location & Routing)?

Yes, they can use searchautocomplete to clean up messy user-provided addresses during a conversation. A coordination agent will request the lookup, and the search agent will return the validated coordinates to the group chat.

Q: How do AutoGen agents handle distance matrices from Jawg Maps (Location & Routing)?

The planning agent calls calculatedistancematrix to get travel times between multiple locations. It then shares this matrix with the scheduling agent, who uses the data to organize driver assignments.

Q: Can I restrict geographic searches to a single country?

Yes, your agents can run searchcountryfilter to ignore any search results outside your target nation. This keeps the conversation focused on relevant locations and prevents the agents from debating invalid routes.

Let your AutoGen agents debate and coordinate optimal routing decisions using real-time Jawg Maps tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jawg Maps (Location & Routing) MCP to AutoGen

Create your Vinkius account to connect Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Route Selection in AutoGen

This MCP server provides `calculate_routing_line` to let your AutoGen agents negotiate the best path between multiple coordinates. One agent can propose a route, while another reviews it for efficiency. They collaborate until they reach a consensus on the optimal path. When coordinates are missing, a search agent runs `search_map_places` to resolve the addresses first. It shares the coordinates in the group chat so the routing agent can immediately calculate the lines. This turns complex logistics planning into a structured, automated team effort.

Analyze Elevation Profiles via Multi-Agent Debate

The `calculate_elevation_routing` tool lets your agents factor terrain slopes into their routing decisions. A performance agent might push for the absolute fastest route, while a fuel-efficiency agent uses the elevation data to argue for a flatter path. They weigh the trade-offs dynamically based on your prompt parameters. Our MCP server also exposes `get_path_elevation` for specific coordinates along the disputed path. This gives the agents hard metrics to back up their arguments. The final decision is mathematically sound and optimized for your specific vehicle types.

Manage Delivery Zones in Agent Conversations

Running `calculate_reachability_isochrone` via this MCP server allows your dispatch agent to define exact delivery boundaries during user interactions. If a user asks for delivery, the agent checks if they fall within the time-based reachability polygon. It then discusses the findings with a pricing agent to calculate delivery fees. For distance-based limits, the group calls `calculate_distance_isochrone` to verify coverage. If the location is borderline, the agents negotiate a custom delivery charge in real time. You get a flexible, automated dispatch system that doesn't require hardcoded rules.

Setup guide

Set up Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) 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="Jawg Maps (Location & Routing)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Jawg Maps (Location & Routing) 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="Jawg Maps (Location & Routing)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Jawg Maps (Location & Routing) 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 Jawg Maps. 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 Jawg Maps (Location & Routing) 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 Jawg Maps (Location & Routing) MCP in AutoGen

Install the extension with `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` pointing to your Vinkius MCP endpoint, and pass the resulting tools list straight to your `AssistantAgent` constructor.

Yes, they can use `search_autocomplete` to clean up messy user-provided addresses during a conversation. A coordination agent will request the lookup, and the search agent will return the validated coordinates to the group chat.

The planning agent calls `calculate_distance_matrix` to get travel times between multiple locations. It then shares this matrix with the scheduling agent, who uses the data to organize driver assignments.

Yes, your agents can run `search_country_filter` to ignore any search results outside your target nation. This keeps the conversation focused on relevant locations and prevents the agents from debating invalid routes.

This server only processes the specific waypoint coordinates and address queries sent during agent execution. Vinkius runs the server in an ephemeral container with zero-trust networking, meaning your spatial data is never cached or written to persistent storage.

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