GeoServer MCP Server

A Model Context Protocol (MCP) server that exposes GeoServer REST API functionality for natural language interaction through AI assistants like Claude, VS Code Copilot, and other MCP-compatible clients.

About

This MCP server wraps the python-geoservercloud library, exposing 80+ GeoServer operations as MCP tools. This enables AI assistants to manage GeoServer workspaces, datastores, layers, styles, and more through natural language commands.

Example Interactions

Once connected, you can ask your AI assistant things like:

• "List all workspaces in GeoServer"
• "Create a new workspace called 'test_data'"
• "What layers are available in the 'topp' workspace?"
• "Create a PostGIS datastore connection"

Installation

From PyPI

pip install geoservercloud-mcp

Or use uvx to run without installing (requires uv):

# Install uv first (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Run the MCP server
uvx geoservercloud-mcp

From MCP Registry

This server is published to the MCP Registry as:

io.github.ronitjadhav/geoservercloud-mcp

Connecting to AI Clients

VS Code / Cursor

Add to your MCP configuration (.vscode/mcp.json):

{
  "servers": {
    "geoserver": {
      "command": "uvx",
      "args": ["geoservercloud-mcp"],
      "env": {
        "GEOSERVER_URL": "http://localhost:8080/geoserver",
        "GEOSERVER_USER": "admin",
        "GEOSERVER_PASSWORD": "geoserver"
      }
    }
  }
}

Claude Desktop

Add to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "geoserver": {
      "command": "uvx",
      "args": ["geoservercloud-mcp"],
      "env": {
        "GEOSERVER_URL": "http://localhost:8080/geoserver",
        "GEOSERVER_USER": "admin",
        "GEOSERVER_PASSWORD": "geoserver"
      }
    }
  }
}

Restart Claude Desktop after saving the configuration.

Claude Code

Add the server with the claude mcp add command:

claude mcp add geoserver \
  --env GEOSERVER_URL=http://localhost:8080/geoserver \
  --env GEOSERVER_USER=admin \
  --env GEOSERVER_PASSWORD=geoserver \
  -- uvx geoservercloud-mcp

This adds it at the default local (per-project) scope. Use --scope user to make it available in all your projects, or --scope project to write it to a shared .mcp.json committed in the repo. Omit the --env flags to configure the connection at runtime instead (the AI will ask for the URL and credentials).

Manage it with:

claude mcp list
claude mcp get geoserver
claude mcp remove geoserver

Dynamic Configuration (No Hardcoded Credentials)

You can omit the env section entirely. The AI will ask you for the GeoServer URL, username, and password at runtime:

{
  "mcpServers": {
    "geoserver": {
      "command": "uvx",
      "args": ["geoservercloud-mcp"]
    }
  }
}

Environment Variables

Python Library

This MCP server is built on the python-geoservercloud library. For programmatic access without MCP, see the library documentation.

from geoservercloud import GeoServerCloud

geoserver = GeoServerCloud(
    url="http://localhost:8080/geoserver",
    user="admin",
    password="geoserver",
)
geoserver.create_workspace("my_workspace")

Full documentation: https://camptocamp.github.io/python-geoservercloud/

Development

For local development, testing, and publishing, see the Developer Guide.