How to Use the ArcGIS MCP in Claude Code

Run ArcGIS spatial analysis, batch geocoding, and fleet routing directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ArcGIS MCP to Claude Code

Create your Vinkius account to connect ArcGIS to Claude Code 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 ArcGIS with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script batch geocoding with Claude Code

The `batch_geocode_addresses` tool processes up to 1000 addresses per request directly from your command line. You pipe a messy CSV file into Claude Code, and it formats the required JSON array string, hits the ArcGIS MCP Server, and spits out the exact coordinates. This works perfectly inside a cron job that cleans up daily customer signups before they hit your production database. For single lookups, the `find_address_candidates` tool converts text inputs into latitude and longitude. If you need strict regional boundaries, calling `find_address_country` filters the results to specific ISO codes like USA or BRA. Your terminal agent handles the entire flow, letting you geocode logs or user records without ever opening a browser or writing a Python script.

Calculate fleet logistics in CI/CD

The `solve_vehicle_routing` tool computes optimal delivery routes for entire fleets using an ArcGIS Orders JSON mapping string. You can trigger Claude Code from a GitHub Action, feed it tomorrow's delivery schedule, and let it generate the optimized stop sequence. It outputs the final routing data as a JSON artifact that your mobile app pulls down at sunrise. Standard point-to-point calculations rely on the `solve_nav_route` tool. You pass a sequence of lon,lat coordinates through the CLI, and it returns travel time, distance, and turn-by-turn directions. DevOps engineers use this to automatically calculate physical distances between new data centers and regional offices during infrastructure planning.

Automate service area analysis

The `calculate_service_area` tool generates precise drive-time and walk-time boundaries around specific coordinates. You run a single terminal command passing your facility locations, and Claude Code queries the MCP Server to return the polygon data. This lets you automatically update service coverage maps on your website every time you open a new store. Matrix routing runs through the `calculate_od_matrix` tool. It determines travel times and distances across multiple origins and destinations at once. You can pipe a list of warehouses and retail stores into your terminal, and the agent will compute the entire matrix, outputting a clean report of the most efficient supply chain routes.

Setup guide

Set up ArcGIS MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see arcgis-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest ArcGIS transactions." It will automatically discover and invoke the available ArcGIS tools.

Terminal

claude mcp add --transport http arcgis-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the ArcGIS MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "arcgis-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 ArcGIS. 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 ArcGIS 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 ArcGIS MCP in Claude Code

Run the add command in your terminal using the HTTP transport flag. You must place all flags before the server name, followed by the Vinkius MCP endpoint URL. Run the list command afterward to verify the connection.

Yes. You can execute headless commands inside any CI/CD pipeline. The agent reads your target files, hits the geocoding endpoint, and commits the updated coordinates back to your repository automatically.

The suggest geocoding tool returns autocomplete results for partial addresses. You can use it to build an interactive command-line prompt that validates user location input before executing a full search.

The agent receives the raw matrix data and formats it based on your prompt. You can ask it to pipe the travel times into a CSV file, output a JSON object, or print a formatted table directly to stdout.

Vinkius isolates every terminal request inside a single-use sandbox. Your warehouse locations and customer addresses pass through memory to execute the calculation. We terminate the instance immediately, leaving zero traces of your spatial data on our servers.

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