docs: update README with container usage and new features

- Add Quick Start guide using ghcr.io Container image
- Document new list_organization_skills tool
- Add instructions for running in HTTP/SSE mode

Author: failattu

README.md

@@ -1,41 +1,61 @@
 # Agileday MCP Server
 
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
-[![Docker](https://img.shields.io/badge/docker-ready-blue.svg)](https://www.docker.com/)
+[![Docker](https://img.shields.io/badge/docker-ghcr.io-blue.svg)](https://github.com/eficode/mcp-agileday/pkgs/container/mcp-agileday)
 
-A [Model Context Protocol (MCP)](https://github.com/modelcontextprotocol) server for **Agileday**.
+A Model Context Protocol (MCP) server for Agileday.
 
-This server bridges Agileday's competence and employee data with LLMs (like Claude Desktop). It allows you to ask natural language questions about your organization's skills, finding experts, and viewing competence profiles without leaving your chat interface.
+This server bridges Agileday's competence and employee data with LLMs (like Claude Desktop or Cursor). It allows you to ask natural language questions about your organization's skills, find experts, and explore competence profiles.
 
 ## Capabilities
 
 This server implements the following tools:
 
-* **`find_experts_with_skill`**: Search for employees who possess a specific skill or competence (e.g., "Who knows React?").
-* **`get_employee_competence_profile`**: Retrieve a full list of skills and proficiency levels for a specific employee.
-
-## Prerequisites
-
-* **Agileday Account:** You need an active Agileday workspace.
-* **API Token:** An API Bearer token from Agileday.
-* **Tenant ID:** Your company slug (e.g., if your URL is `acme.agileday.io`, your tenant ID is `acme`).
-* **MCP Client:** An application that supports MCP, such as [Claude Desktop](https://claude.ai/download).
+* **find_experts_with_skill**
+    * *Query:* "Who knows React?"
+    * *Action:* Searches for employees who possess a specific skill and returns their proficiency levels.
+* **get_employee_competence_profile**
+    * *Query:* "What are Jane Doe's top skills?"
+    * *Action:* Retrieves a full list of skills, proficiency levels, and motivation for a specific employee.
+* **list_organization_skills**
+    * *Query:* "What skills do we have in the organization?"
+    * *Action:* Retrieves the full taxonomy of skills available in your Agileday workspace, grouped by category. This helps the AI understand exactly which terms to search for and avoids guessing.
 
 ## Configuration
 
-The server requires the following environment variables:
+You need the following environment variables to run the server:
 
 | Variable | Description | Example |
 | :--- | :--- | :--- |
-| `AGILEDAY_TENANT_ID` | Your specific Agileday subdomain. | `acme` |
+| `AGILEDAY_TENANT_ID` | Your company slug (subdomain). | `acme` (for `acme.agileday.io`) |
 | `AGILEDAY_API_TOKEN` | Your API Bearer token. | `eyJhbGciOi...` |
 
-## Installation & Usage
-
-You can run this server using Docker (recommended) or directly with Python.
+## Quick Start (Docker)
+
+The easiest way to run the server is using the pre-built Docker image from the GitHub Container Registry.
+
+### 1. Run with Claude Desktop
+Add this configuration to your `claude_desktop_config.json`:
+
+```json
+{
+  "mcpServers": {
+    "agileday": {
+      "command": "docker",
+      "args": [
+        "run",
+        "-i",
+        "--rm",
+        "-e", "AGILEDAY_TENANT_ID=your_tenant_id",
+        "-e", "AGILEDAY_API_TOKEN=your_api_token",
+        "ghcr.io/eficode/mcp-agileday:latest"
+      ]
+    }
+  }
+}
 
-### Option 1: Docker (Recommended)
+### Option 2: Docker
 
 1.  **Clone the repository:**
     ```bash
@@ -71,7 +91,7 @@ You can run this server using Docker (recommended) or directly with Python.
 
 4.  **Restart Claude Desktop.**
 
-### Option 2: Local Python
+### Option 3: Local Python
 
 1.  **Clone the repository and install dependencies:**
     ```bash
@@ -97,6 +117,24 @@ You can run this server using Docker (recommended) or directly with Python.
       }
     }
     ```
+    
+### Option 4: Run as service
+To deploy this as a standalone service (e.g., for remote access or clients that support HTTP transport), use the http transport mode.
+
+    ```bash
+      docker run -d \
+        -p 8000:8000 \
+        -e AGILEDAY_TENANT_ID=your_tenant \
+        -e AGILEDAY_API_TOKEN=your_token \
+        ghcr.io/eficode/mcp-agileday:latest \
+        --transport http
+    ```
+
+The server will be available at:
+
+Universal Endpoint: http://localhost:8000/mcp (Supports both SSE stream and POST messages)
+
+Health Check: http://localhost:8000/health
 
 ## Example Prompts