mcp -demo-ERPNEXT
MCP server from Orm15/mcp-server-demo-ERPNEXT
claude mcp add --transport stdio orm15-mcp-server-demo-erpnext uvx mcp
How to use
This MCP server exposes tools that integrate with ERPNext through the MCP (Model Context Protocol) framework. It registers Python functions as accessible tools that a chatbot or external interface can call to interact with ERPNext data, such as assigning a professor to a sales order and other ERPNext-related operations described in the project. To use it locally, ensure the ERP connection details are configured and the MCP server is running so that assistants can invoke the exposed tools. The server leverages a development flow where you run the MCP service with UV (uv run mcp) and then call the available tools via the chat or MCP Inspector / clipboard-based interfaces. The README mentions a specific example function to assign a professor to a sales order, which updates the ERPNext record and returns the operation result.
How to install
Prerequisites:
- Python installed on your system
- Access to a running ERPNext instance and the necessary API credentials (URL, API key, API secret)
Step 1: Install Python and package manager utilities
- Ensure Python is installed (preferably Python 3.8+)
- Install uv (Python utility) via pipx or pip:
- If using pipx:
pip install pipx pipx install uv - If using pip:
pip install uv
- If using pipx:
Step 2: Prepare project dependencies
- In the project root, install dependencies from requirements.txt if present:
uv pip install -r requirements.txt
Step 3: Configure ERPNext connection
- Create a .env file in the project root with your ERPNext settings:
URL_ERPNext=http://your-erpnext-host/ API_KEY=your_api_key API_SECRET=your_api_secret
Step 4: Run the MCP server
- Start the MCP server using uv:
uv run mcp
Step 5: Verify and test
- Use the MCP Inspector or your connected chatbot to verify that the exposed tools are available and functioning against ERPNext.
Optional: If you encounter issues with permissions or environment setup, consider running the commands with elevated privileges or adjusting your Python environment accordingly.
Additional notes
Notes and tips:
- The MCP server exposes ERPNext-related functions (e.g., asignar_profesor_a_orden_venta) as tools. Ensure the ERPNext user has appropriate permissions to update sales orders.
- Keep your ERPNext URL and API credentials secure. Do not commit .env files to version control.
- If running on Windows, you may need appropriate shell environments (PowerShell or CMD) and ensure uv is accessible in your PATH.
- When testing tools in GitHub Copilot chat or MCP Inspector, ensure the server is reachable from the test client and that the tool names match those registered in the MCP server.
- The configuration in this project uses UV to run the MCP server; you may switch to other transport modes if supported by your deployment environment.
Related MCP Servers
mcp-vegalite
MCP server from isaacwasserman/mcp-vegalite-server
github-chat
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
pagerduty
PagerDuty's official local MCP (Model Context Protocol) server which provides tools to interact with your PagerDuty account directly from your MCP-enabled client.
futu-stock
mcp server for futuniuniu stock
mcp -boilerplate
Boilerplate using one of the 'better' ways to build MCP Servers. Written using FastMCP