docs

Author: lkrzyzanek

CONTRIBUTING.md

@@ -19,6 +19,8 @@ Install [Pants Build](https://www.pantsbuild.org/stable/docs/getting-started/ins
 
 On Linux, you can run `./get-pants.sh` available in the repo root, as described/recommended in the Pants Installation docs.
 
+Install [Podman](https://podman.io/) to be able build images like `Next Gen UI MCP Server`.
+
 ### VSCode
 
 Run Pants export to create a virtual env
@@ -88,6 +90,12 @@ pants run libs/next_gen_ui_llama_stack/agent_test.py
 
 # Run formatter, linter, check
 pants fmt lint check ::
+
+# Build all packages including python and docker
+pants package ::
+
+# Build only Python packages
+pants package --filter-target-type=python_distribution ::
 ```
 
 ### Dependency Management

docs/guide/ai_apps_binding/index.md

@@ -11,7 +11,7 @@ Binding UI Agent core functionality into your AI application (AI assistant backe
 
 ## AI Protocol bindings/servers
 
-* MCP - WIP
+* MCP - [MCP Library](mcp.md) and [MCP Container](mcp-containers.md)
 * A2A - WIP
 * [ACP](acp.md) - Tech Preview
 

docs/guide/ai_apps_binding/mcp-container.md

@@ -0,0 +1,3 @@
+{%
+    include-markdown "../../../libs/next_gen_ui_mcp/README-containers.md"
+%}

docs/guide/ai_apps_binding/mcp-library.md

@@ -0,0 +1,3 @@
+{%
+    include-markdown "../../../libs/next_gen_ui_mcp/README.md"
+%}

libs/next_gen_ui_mcp/README-containers.md

@@ -1,4 +1,4 @@
-# Next Gen UI MCP Server
+# Next Gen UI MCP Server Container
 
 Next Gen UI MCP Server container image.
 
@@ -32,7 +32,42 @@ The MCP server container can be configured via environment variables. All config
 | `NGUI_MODEL`                 | `gpt-4o`          | Model name (required for non-MCP providers)            |
 | `NGUI_PROVIDER_API_BASE_URL` | -                 | Base URL for OpenAI-compatible API                     |
 | `NGUI_PROVIDER_API_KEY`      | -                 | API key for the LLM provider                           |
-| `NGUI_PROVIDER_LLAMA_URL`    | -                 | LlamaStack server URL (if `llamastac` is used)         |
+| `NGUI_PROVIDER_LLAMA_URL`    | -                 | LlamaStack server URL (if `llamastack` is used)         |
+
+### Providers
+
+The Next Gen UI MCP server supports three inference providers, controlled by the `NGUI_PROVIDER` environment variable:
+
+Selects the inference provider to use for generating UI components:
+
+#### Provider **`mcp`** 
+
+Uses Model Context Protocol sampling to leverage the client's LLM capabilities. No additional configuration required as it uses the connected MCP client's model.
+
+#### Provider **`langchain`**:
+
+Uses LangChain with OpenAI-compatible APIs.
+
+Requires:
+
+- `NGUI_MODEL`: Model name (e.g., `gpt-4o`, `llama3.2`)
+- `NGUI_PROVIDER_API_KEY`: API key for the provider
+- `NGUI_PROVIDER_API_BASE_URL` (optional): Custom base URL for OpenAI-compatible APIs like Ollama
+
+Examples:
+
+- OpenAI: `https://api.openai.com/v1` (default)
+- Ollama: `http://host.containers.internal:11434/v1`
+
+#### Provider **`llamastack`**:
+
+Uses LlamaStack server for inference.
+
+Requires:
+
+  - `NGUI_MODEL`: Model name available on the LlamaStack server
+  - `NGUI_PROVIDER_LLAMA_URL`: URL of the LlamaStack server
+
 
 ### Usage Examples
 
@@ -84,6 +119,7 @@ podman run --rm -it -p 5000:5000 \
 ### Network Configuration
 
 For local development connecting to services running on the host machine:
+
 - Use `host.containers.internal` to access host services (works with Podman and Docker Desktop)
 - For Linux with Podman, you may need to use `host.docker.internal` or the host's IP address
 - Ensure the target services (like Ollama) are accessible from containers

libs/next_gen_ui_mcp/README.md

@@ -1,4 +1,4 @@
-# Next Gen UI MCP Server
+# Next Gen UI MCP Server Library
 
 This package wraps our NextGenUI agent in a Model Context Protocol (MCP) tool using the standard MCP SDK. Since MCP adoption is so strong these days and there is an apetite to use this protocol also for handling agentic AI, we wanted to also deliver this way of consuming our agent. The most common way of utilising MCP tools is to provide them to LLM to choose and execute with certain parameters. This approach doesn't make sense for NextGenUI agent as you want to call it at specific moment after gathering data for response and also you don't want LLM to try to pass the prompt and JSON content as it may lead to unnecessary errors in the content. It's more natural and reliable to invoke this MCP tool directly with the parameters as part of your main application logic.
 
@@ -80,16 +80,21 @@ result = client.tool_runtime.invoke_tool(tool_name="generate_ui", kwargs=input_d
 ## Available MCP Tools
 
 ### `generate_ui`
-The main tool that wraps the entire Next Gen UI Agent functionality. This single tool handles:
+The main tool that wraps the entire Next Gen UI Agent functionality.
+
+This single tool handles:
+
 - Component selection based on user prompt and data
 - Data transformation to match selected components  
 - Design system rendering to produce final UI
 
 **Parameters:**
+
 - `user_prompt` (str): User's prompt which we want to enrich with UI components
 - `input_data` (List[Dict]): List of input data to render within the UI components
 
 **Returns:**
+
 - List of rendered UI components ready for display
 
 ## Available MCP Resources

mkdocs.yml

@@ -80,6 +80,8 @@ nav:
       - Embedded Llama Stack Server: guide/ai_apps_binding/llamastack_embedded.md
       - BeeAI: guide/ai_apps_binding/beeai.md
       - ACP: guide/ai_apps_binding/acp.md
+      - MCP Library: guide/ai_apps_binding/mcp-library.md
+      - MCP Container: guide/ai_apps_binding/mcp-container.md
       - Python Library: guide/ai_apps_binding/pythonlib.md
     - Binding into UI:
       - guide/renderer/index.md