Merge pull request #5 from latinogino/codex/cleanup-unnecessary-files-and-scripts

Clarify Windows setup for Claude Desktop

CHANGELOG.md

@@ -4,8 +4,6 @@ All notable changes to the Dolibarr MCP Server are documented here. The project
 follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and adopts the
 [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.
 
-## [Unreleased]
-
 ### Added
 - Restored README.md and CHANGELOG.md after merge conflicts while preserving the streamlined structure shared with `prestashop-mcp`.
 - Documented platform-specific setup covering Linux/macOS shells, Windows Visual Studio `vsenv`, and the Docker workflow.
@@ -28,8 +26,6 @@ follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and adopts th
 - Rewrote the README to highlight the streamlined structure and provide concise installation/run instructions.
 - Clarified that `dolibarr_mcp_server.py` is the definitive MCP entry point.
 
-## [Unreleased]
-
 ## [1.1.0] - 2024-05-22
 
 ### Removed

README.md

@@ -1,7 +1,16 @@
 # Dolibarr MCP Server
 
 Dolibarr MCP is a focused Model Context Protocol (MCP) server that exposes the
-most useful Dolibarr ERP/CRM operations to AI copilots.
+most useful Dolibarr ERP/CRM operations to AI copilots. The repository mirrors
+the clean layout used by [`prestashop-mcp`](https://github.com/latinogino/prestashop-mcp):
+a single production-ready server implementation, an async HTTP client, and a
+self-contained documentation bundle.
+
+
+This MCP server enables complete management of your Dolibarr ERP/CRM through AI
+tools such as Claude Desktop. With specialised tools you can manage customers,
+products, invoices, orders, contacts, and system administration tasks from a
+single MCP endpoint.
 
 This MCP server enables complete management of your Dolibarr ERP/CRM through AI
 tools such as Claude Desktop. With specialised tools you can manage customers,
@@ -62,11 +71,11 @@ pip install -e '.[dev]'
 ### Windows (Visual Studio `vsenv`)
 
 1. Launch the **x64 Native Tools Command Prompt for VS** or **Developer PowerShell for VS** (`vsenv`).
-2. Create a virtual environment: `py -3 -m venv .venv`.
+2. Create a virtual environment next to the repository root: `py -3 -m venv .venv`.
 3. Activate it: `call .venv\\Scripts\\activate.bat` (Command Prompt) or `.\\.venv\\Scripts\\Activate.ps1` (PowerShell).
 4. Install the package: `pip install -e .`.
 5. Install development extras when required: `pip install -e .[dev]` (PowerShell requires escaping brackets: ``pip install -e .`[dev`]``).
-6. Note the Python path (`where python`) for integration with Claude Desktop or other MCP hosts.
+6. Run `where python` **inside** the activated environment and copy the reported path. Claude Desktop must use this exact `python.exe`; mismatched paths (for example, pointing at a non-existent `venv_dolibarr\Scripts\python.exe`) will produce an immediate `ENOENT` error and the server will show as *disconnected*.
 
 ### Docker
 
@@ -127,8 +136,6 @@ MCP server.
 - Contributions follow the same structure and documentation conventions as
   `prestashop-mcp` to keep the twin projects in sync.
 
-## 📄 License
-=======
 ```bash
 python -m dolibarr_mcp.cli test --url https://your-dolibarr.example.com/api/index.php --api-key YOUR_KEY
 ```
@@ -144,7 +151,6 @@ python -m dolibarr_mcp.cli test --url https://your-dolibarr.example.com/api/inde
 - **Contacts** – `get_contacts`, `get_contact_by_id`, `create_contact`, `update_contact`, `delete_contact`
 - **Raw API access** – `dolibarr_raw_api`
 
-
+## 📄 License
-## License
 
 This project is released under the [MIT License](LICENSE).

docs/configuration.md

@@ -6,7 +6,7 @@ host application that will launch the server.
 
 | Variable            | Description                                                    |
 | ------------------- | -------------------------------------------------------------- |
-| `DOLIBARR_URL`      | Base API URL, e.g. `https://your-dolibarr.example.com/api/index.php` |
+| `DOLIBARR_URL`      | Base API URL, e.g. `https://your-dolibarr.example.com/api/index.php` (legacy configs that still export `DOLIBARR_BASE_URL` are also honoured) |
 | `DOLIBARR_API_KEY`  | Personal Dolibarr API token assigned to your user              |
 | `LOG_LEVEL`         | Optional logging level (`INFO`, `DEBUG`, `WARNING`, …)         |
 

docs/quickstart.md

@@ -25,6 +25,7 @@ source .venv/bin/activate
 vsenv
 py -3 -m venv .venv
 .\.venv\Scripts\Activate.ps1
+where python  # copy this path for Claude Desktop
 ```
 
 ## 3. Install the package
@@ -57,4 +58,7 @@ python -m dolibarr_mcp.cli serve
 ```
 
 The command starts the STDIO based MCP server that Claude Desktop and other
-clients can communicate with.
+clients can communicate with. When wiring the server into Claude Desktop, set
+`command` to the path returned by `where python` (Windows) or `which python`
+(Linux/macOS) while the virtual environment is activated, and use the arguments
+`-m dolibarr_mcp.cli serve`.