MCP 服务器

GeoServer MCP Server

A Model Context Protocol server that connects Large Language Models to the GeoServer REST API, enabling AI assistants to query and manipulate geospatial data through natural language.

Tools

create_layer

Create a new layer in GeoServer. Args: workspace: The workspace for the new layer layer: The name of the layer to create data_store: The data store to use source: The source data (file, table name, etc.) Returns: Dict with status and layer information

delete_resource

Delete a resource from GeoServer. Args: resource_type: Type of resource to delete (workspace, layer, style, etc.) workspace: The workspace containing the resource name: The name of the resource Returns: Dict with status and result information

query_features

Query features from a vector layer using CQL filter. Args: workspace: The workspace containing the layer layer: The layer to query filter: Optional CQL filter expression properties: Optional list of properties to return max_features: Maximum number of features to return Returns: GeoJSON FeatureCollection with query results

generate_map

Generate a map image using WMS GetMap. Args: layers: List of layers to include (format: workspace:layer) styles: Optional styles to apply (one per layer) bbox: Bounding box [minx, miny, maxx, maxy] width: Image width in pixels height: Image height in pixels format: Image format (png, jpeg, etc.) Returns: Dict with map information and URL

create_style

Create a new SLD style in GeoServer. Args: name: Name for the style sld: SLD XML content workspace: Optional workspace for the style Returns: Dict with status and style information

list_workspaces

List available workspaces in GeoServer.

create_workspace

Create a new workspace in GeoServer. Args: workspace: Name of the workspace to create Returns: Dict with status and result information

get_layer_info

Get detailed information about a layer. Args: workspace: The workspace containing the layer layer: The name of the layer Returns: Dict with layer metadata

list_layers

List layers in GeoServer, optionally filtered by workspace. Args: workspace: Optional workspace to filter layers Returns: List of layer information dictionaries

README

GeoServer MCP Server

<a href="https://badge.mcpx.dev?type=server 'MCP Server'"> <img src="https://badge.mcpx.dev?type=server" title="MCP Server"/> </a> <p align="center"> A Model Context Protocol (MCP) server implementation that connects Large Language Models (LLMs) to the GeoServer REST API, enabling AI assistants to interact with geospatial data and services. </p>

🏆 Badges & Indexes

🚀 Features

🔍 Query and manipulate GeoServer workspaces, layers, and styles
🗺️ Execute spatial queries on vector data
🎨 Generate map visualizations
🌐 Access OGC-compliant web services (WMS, WFS)
🔄 Real-time interaction with GeoServer REST API
📊 Support for complex spatial operations
🛠️ Easy integration with MCP-compatible clients

📋 Prerequisites

Python 3.10 or higher
Running GeoServer instance with REST API enabled
MCP-compatible client (like Claude Desktop or Cursor)
geoserver-rest package
Internet connection for package installation

🛠️ Installation

Clone the repository:

git clone https://github.com/mahdin75/geoserver-mcp.git
cd geoserver-mcp

Install the package:

pip install -e .

Configure GeoServer connection:

Linux/Mac:

export GEOSERVER_URL="http://localhost:8080/geoserver"
export GEOSERVER_USER="admin"
export GEOSERVER_PASSWORD="geoserver"

Windows PowerShell:

$env:GEOSERVER_URL="http://localhost:8080/geoserver"
$env:GEOSERVER_USER="admin"
$env:GEOSERVER_PASSWORD="geoserver"

Start the server:

geoserver-mcp-server

🔧 Configuration

Command-line Arguments

geoserver-mcp-server --url http://localhost:8080/geoserver --user admin --password geoserver --debug

Environment Variables

Variable	Description	Default
GEOSERVER_URL	GeoServer instance URL	http://localhost:8080/geoserver
GEOSERVER_USER	Admin username	admin
GEOSERVER_PASSWORD	Admin password	geoserver

MCP Client Integration

Claude Desktop

Edit claude_desktop_config.json:

{
  "mcpServers": {
    "geoserver-mcp-server": {
      "command": "geoserver-mcp-server",
      "args": [
        "--url",
        "http://localhost:8080/geoserver",
        "--user",
        "admin",
        "--password",
        "geoserver"
      ]
    }
  }
}

Cursor

Create .cursor/mcp.json:

{
  "mcpServers": {
    "geoserver-mcp-server": {
      "command": "geoserver-mcp-server",
      "args": [
        "--url",
        "http://localhost:8080/geoserver",
        "--user",
        "admin",
        "--password",
        "geoserver"
      ]
    }
  }
}

🛠️ Available Tools

Catalog Management

Tool	Description
`list_workspaces`	Get available workspaces
`create_workspace`	Create a new workspace
`get_layer_info`	Get detailed layer metadata
`list_layers`	List layers in a workspace
`create_layer`	Create a new layer
`delete_resource`	Remove resources

Data Operations

Tool	Description
`query_features`	Execute CQL queries on vector data
`update_features`	Modify feature attributes
`delete_features`	Remove features based on criteria

Visualization

Tool	Description
`generate_map`	Create styled map images
`create_style`	Define new SLD styles
`apply_style`	Apply existing styles to layers

📚 Example Usage

List Workspaces

Tool: list_workspaces
Parameters: {}
Response: ["default", "demo", "topp", "tiger", "sf"]

List of GeoServer Workspaces

Get Layer Information

Tool: get_layer_info
Parameters: {
  "workspace": "topp",
  "layer": "states"
}

Query Features

Tool: query_features
Parameters: {
  "workspace": "topp",
  "layer": "states",
  "filter": "PERSONS > 10000000",
  "properties": ["STATE_NAME", "PERSONS"]
}

Generate Map

Tool: generate_map
Parameters: {
  "layers": ["topp:states"],
  "styles": ["population"],
  "bbox": [-124.73, 24.96, -66.97, 49.37],
  "width": 800,
  "height": 600,
  "format": "png"
}