@pagopa/dx-mcpserver 0.0.1 → 0.0.2

package/README.md

@@ -4,17 +4,6 @@
 
 This package contains the implementation of a Model Context Protocol (MCP) server.
 
-## Architecture
-
-The architecture allows any Model Context Protocol (MCP) compliant client (such as GitHub Copilot) to query the [PagoPA DX technical documentation](https://dx.pagopa.it/) in natural language, receiving contextualized and up-to-date answers.
-
-1.  **Content Upload**: On each release of the documentation website, Markdown and text files (`.md`, `.txt`) are uploaded to an S3 bucket.
-2.  **Indexing**: From there, the documents are processed by **Amazon Bedrock Knowledge Bases**, which handles the embedding and semantic indexing process.
-3.  **Vector Storage**: The resulting embeddings are saved in a Vector Bucket (an S3-based vector database), enabling efficient and persistent semantic search.
-4.  **Query and Retrieval**: When an MCP client sends a query, an **AWS Lambda** function implementing the MCP Server queries the Knowledge Base to retrieve the most relevant content and returns the response to the client.
-
-This approach allows AI agents like Copilot to access the documentation context in a structured way, keeping the orchestration, storage, and semantic retrieval layers separate.
-
 ## Features
 
 The server currently exposes the following capabilities:
@@ -25,16 +14,25 @@ The server currently exposes the following capabilities:
 - **Prompts**:
   - `GenerateTerraformConfiguration`: Guides the generation of Terraform configurations following PagoPA DX best practices.
 
-## How to use it
+## Authentication
+
+The server requires a fine-grained [GitHub Personal Access Token](https://github.com/settings/personal-access-tokens) for authentication with the following settings:
+
+- **Resource owner:**
+  - Choose the **pagopa** organization
+- **Repository access:**
+  - Public Repositories (read-only)
+- **Organization permissions:**
+  - Members: Read-only (to verify membership in the pagopa organization)
+
+## Usage
 
 This server can be used by any MCP-compliant client.
 
-<details>
-<summary><b>VS Code</b></summary>
+### VS Code
 
 Update your configuration file with the following. See [VS Code MCP docs](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more info.
-
-#### VS Code Remote Server Connection
+The GH PAT authentication is done via a prompt, so you will be asked to enter it the first time you use the server.
 
 ```json
 {
@@ -43,17 +41,23 @@ Update your configuration file with the following. See [VS Code MCP docs](https:
       "url": "https://api.dev.dx.pagopa.it/mcp",
       "type": "http",
       "headers": {
-        "x-gh-pat": "${env:GH_PAT}"
+        "x-gh-pat": "${input:github_mcp_pat}"
       }
-    }
+    },
+    "inputs": [
+      {
+        "type": "promptString",
+        "id": "github_mcp_pat",
+        "description": "GitHub Personal Access Token",
+        "password": true
+      }
+    ]
   }
 }
 ```
 
-</details>
+### GitHub Copilot Coding Agent
 
-<details>
-<summary><b>GitHub Copilot Coding Agent</b></summary>
 You need to configure it in the repository settings. See [GitHub Copilot MCP docs](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/coding-agent/extend-coding-agent-with-mcp) for more info.
 
 1.  **Declare the MCP Server**: In the "Copilot" >> "Coding agent" panel of your repository settings, add an MCP Server declaration as follows:
@@ -77,7 +81,19 @@ You need to configure it in the repository settings. See [GitHub Copilot MCP doc
 
 Once configured, Copilot can autonomously invoke the MCP server's tools during task execution, using it to access documentation context and improve the quality of its code generation.
 
-</details>
+### GitHub Copilot CLI
+
+To use the MCP server with [GitHub Copilot CLI](https://github.com/features/copilot/cli/), run the cli with `copilot` and prompt `/mcp add` to start the configuration of the MCP server
+
+Follow the guided wizard to start using the DX MCP server:
+
+1. **Server Name**: `dx-docs`
+2. **Server Type**: `2` (HTTP)
+3. **URL**: `https://api.dev.dx.pagopa.it/mcp`
+4. **HTTP Headers**: `{"x-gh-pat": "<your-gh-PAT>"}`
+5. **Tools**: `*` (leave as is)
+
+Use `Tab` to navigate between fields and `Ctrl+S` to save.
 
 ## Development
 
@@ -102,3 +118,14 @@ To build the Docker container for this application, run the following command fr
 ```bash
 docker build -t dx/mcp-server -f ./apps/mcpserver/Dockerfile .
 ```
+
+## Architecture
+
+The architecture allows any Model Context Protocol (MCP) compliant client (such as GitHub Copilot) to query the [PagoPA DX technical documentation](https://dx.pagopa.it/) in natural language, receiving contextualized and up-to-date answers.
+
+1.  **Content Upload**: On each release of the documentation website, Markdown and text files (`.md`, `.txt`) are uploaded to an S3 bucket.
+2.  **Indexing**: From there, the documents are processed by **Amazon Bedrock Knowledge Bases**, which handles the embedding and semantic indexing process.
+3.  **Vector Storage**: The resulting embeddings are saved in a Vector Bucket (an S3-based vector database), enabling efficient and persistent semantic search.
+4.  **Query and Retrieval**: When an MCP client sends a query, an **AWS Lambda** function implementing the MCP Server queries the Knowledge Base to retrieve the most relevant content and returns the response to the client.
+
+This approach allows AI agents like Copilot to access the documentation context in a structured way, keeping the orchestration, storage, and semantic retrieval layers separate.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pagopa/dx-mcpserver",
-  "version": "0.0.1",
+  "version": "0.0.2",
   "type": "module",
   "description": "An MCP server that support developers using DX tools.",
   "repository": {
@@ -32,6 +32,7 @@
     "@types/node": "^22.16.2",
     "@vitest/coverage-v8": "^3.2.4",
     "eslint": "^9.30.0",
+    "prettier": "3.6.2",
     "typescript": "~5.8.3",
     "vitest": "^3.2.4",
     "@pagopa/eslint-config": "^5.1.0"