Closed — opened by mistake

.gitignore

@@ -4,3 +4,12 @@
 /.venv/
 .coverage
 docs/build
+
+# MCP Registry tokens (security sensitive)
+.mcpregistry_github_token
+.mcpregistry_registry_token
+
+# Build artifacts
+dist/
+*.whl
+*.tar.gz

README.md

@@ -1,149 +1,130 @@
-# python-geoservercloud
+# GeoServer MCP Server
 
-## Documentation
+<!-- mcp-name: io.github.ronitjadhav/geoservercloud-mcp -->
 
-https://camptocamp.github.io/python-geoservercloud/
+A Model Context Protocol (MCP) server that exposes [GeoServer](https://geoserver.org/) 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](docs/LIBRARY.md) 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:
+### From PyPI
 
-```shell
-pip install geoservercloud
+```bash
+pip install geoservercloud-mcp
 ```
 
-From git repository:
+Or use `uvx` to run without installing (requires [uv](https://docs.astral.sh/uv/)):
 
-```shell
-git clone https://github.com/camptocamp/python-geoservercloud
-cd python-geoservercloud
-python3 -m venv .venv
-source .venv/bin/activate
-poetry install
+```bash
+# Install uv first (if not already installed)
+curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Run the MCP server
+uvx geoservercloud-mcp
 ```
 
-## Quick start
+### From MCP Registry
 
-```python
-from geoservercloud import GeoServerCloud
+This server is published to the [MCP Registry](https://registry.modelcontextprotocol.io) as:
 
-geoserver = GeoServerCloud(
-    url="http://localhost:9090/geoserver/cloud/",
-    user="admin",
-    password="geoserver",
-)
-geoserver.create_workspace("newworkspace")
+```text
+io.github.ronitjadhav/geoservercloud-mcp
 ```
 
-## About
+---
 
-Lightweight Python client to interact with GeoServer Cloud REST API, GeoServer ACL and OGC services.
-Intended use cases are listed below.
+## Connecting to AI Clients
 
-### Programmatic setup of a GeoServer catalog
+### VS Code / Cursor
 
-For example, creating a workspace, connecting to a PostGIS datastore and publishing a PG layer:
+Add to your MCP configuration (`.vscode/mcp.json`):
 
-```python
-geoserver.create_workspace("example")
-geoserver.create_pg_datastore(
-    workspace_name="example",
-    datastore_name="example_store",
-    pg_host="localhost",
-    pg_port=5432,
-    pg_db="database",
-    pg_user="user",
-    pg_password="password"
-)
-geoserver.create_feature_type(
-    layer_name="layer_example",
-    workspace_name="example",
-    datastore_name="example_store",
-    title={
-        "en":"Layer title",
-        "fr": "Titre de la couche",
-        "default": "Default title",
-    },
-)
+```json
+{
+  "servers": {
+    "geoserver": {
+      "command": "uvx",
+      "args": ["geoservercloud-mcp"],
+      "env": {
+        "GEOSERVER_URL": "http://localhost:8080/geoserver",
+        "GEOSERVER_USER": "admin",
+        "GEOSERVER_PASSWORD": "geoserver"
+      }
+    }
+  }
+}
 ```
 
-### Testing
+### Claude Desktop
+
+Add to your Claude Desktop config:
+
+**macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`  
+**Linux:** `~/.config/Claude/claude_desktop_config.json`
+
+```json
+{
+  "mcpServers": {
+    "geoserver": {
+      "command": "uvx",
+      "args": ["geoservercloud-mcp"],
+      "env": {
+        "GEOSERVER_URL": "http://localhost:8080/geoserver",
+        "GEOSERVER_USER": "admin",
+        "GEOSERVER_PASSWORD": "geoserver"
+      }
+    }
+  }
+}
+```
 
-Automatic tests of GeoServer functionalities with `pytest`, for example before upgrading.
-The example below tests the fallback mechanism for internationalized layer titles in the GetCapabilities document.
+Restart Claude Desktop after saving the configuration.
 
-```python
-@pytest.mark.parametrize(
-    "language,expected_title",
-    [
-        (
-            "en",
-            "Layer title",
-        ),
-        (
-            "fr",
-            "Titre de la couche",
-        ),
-        (
-            "de,en",
-            "Layer title",
-        ),
-        (
-            None,
-            "Default title",
-        ),
-    ],
-)
-def test_i18n_layer_title(geoserver, language, expected_title):
-    capabilities = geoserver.get_wms_layers(
-        workspace="example",
-        accept_languages=language,
-    )
-    layer = capabilities.get("Layer")
-    assert layer.get("Title") == expected_title
-```
+---
+
+## Environment Variables
 
-A test suite is provided in the directory `geoserver_acceptance_tests`.
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `GEOSERVER_URL` | `http://localhost:8080/geoserver` | GeoServer base URL |
+| `GEOSERVER_USER` | `admin` | GeoServer username |
+| `GEOSERVER_PASSWORD` | `geoserver` | GeoServer password |
 
-### Syncing
+---
 
-Copying a workspace from one GeoServer instance to another, including PG datastores, layers, styles and style images.
+## Python Library
 
-#### In a Python console or script
+This MCP server is built on the **python-geoservercloud** library. For programmatic access without MCP, see the [library documentation](docs/LIBRARY.md).
 
 ```python
-from geoservercloud import GeoServerCloudSync
-geoserversync = GeoServerCloudSync(
-    src_url="http://localhost:8080/geoserver",
-    src_user="admin",
-    src_password="geoserver",
-    dst_url="http://localhost:9099/geoserver",
-    dst_user="admin",
-    dst_password="geoserver",
+from geoservercloud import GeoServerCloud
+
+geoserver = GeoServerCloud(
+    url="http://localhost:8080/geoserver",
+    user="admin",
+    password="geoserver",
 )
-geoserversync.copy_workspace("workspace_name", deep_copy=True)
+geoserver.create_workspace("my_workspace")
 ```
 
-#### In a shell terminal or script
-
-First install the package in your current virtual environment (see [Installation](#installation)), then run the script with:
+Full documentation: <https://camptocamp.github.io/python-geoservercloud/>
 
-```shell
-copy-workspace --src_url "http://localhost:8080/geoserver" --src_user admin --src_password geoserver --dst_url "http://localhost:9099/geoserver" --dst_user admin --dst_password geoserver --workspace workspace_name
-```
-
-### Logging
+---
 
-Set the log level using the standard `logging` module, e.g.:
+## Development
 
-```python
-import logging
-
-gs_logger = logging.getLogger("geoservercloud")
-gs_logger.setLevel(logging.DEBUG)
-handler = logging.StreamHandler()
-handler.setLevel(logging.DEBUG)
-formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-handler.setFormatter(formatter)
-gs_logger.addHandler(handler)
-```
+For local development, testing, and publishing, see the [Developer Guide](docs/DEVELOPER.md).