How to Use the Mapflow MCP in Claude Code

Q: How do I connect the Mapflow MCP Server to Claude Code?

Run claude mcp add --transport http mapflow -- . Make sure you put all flags before the server name. The config saves to /.claude.json.

Automate geospatial feature extraction 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 Mapflow MCP to Claude Code

Create your Vinkius account to connect Mapflow 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 Mapflow with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless extraction with this MCP Server.

Scripting this is straightforward. `list_models` outputs the available AI models straight to stdout, letting you pipe the results to dynamically select the right engine for building detection. Project initialization takes one command. The CLI triggers `create_project` to spin up a new workspace, returning the ID needed for the rest of your pipeline.

Queuing jobs from the command line.

You can trigger this from a GitHub Action whenever new coordinates drop into your database. `create_processing` takes a JSON string of your target area and pushes it to the API. The terminal handles the waiting game. Your script loops `get_processing_status` to monitor the queue, blocking the next CI/CD step until the analysis hits 100 percent.

Dumping results to standard output.

`get_processing_result` downloads the finalized feature collection. You can pipe the resulting GeoJSON directly into jq or a Postgres database for immediate use. Auditing is fast and scriptable. Running `list_processings` or `list_projects` gives you a quick JSON array of everything running, perfect for automated cleanup cron jobs.

Setup guide

Set up Mapflow 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 mapflow-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http mapflow-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 Mapflow 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": {
    "mapflow-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 Mapflow. 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 Mapflow 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 Mapflow MCP in Claude Code

Run `claude mcp add --transport http mapflow -- `. Make sure you put all flags before the server name. The config saves to `~/.claude.json`.

Yes. You can write a bash script that calls the CLI, passes in your target coordinates, and handles the extraction entirely headlessly.

The tools return plain JSON strings. You can pipe the response from the results endpoint directly into tools like `jq` to extract the specific polygon arrays you need.

The CLI will keep polling the status endpoint until it gets a success or failure state. You can adjust your script's timeout settings to handle massive high-resolution imagery requests.

No. The connection relies on a single endpoint token, and your raw polygon coordinates pass through a zero-trust architecture. The isolated sandbox drops all state the moment the data pipeline finishes executing.

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