Infrastructure that connects LLMs to ERPNext. Frappe Assistant Core works with the Model Context Protocol (MCP) to expose ERPNext functionality to any compatible Language Model
# Add to your Claude Code skills
git clone https://github.com/buildswithpaul/Frappe_Assistant_Core🔧 LLM Integration Platform for ERPNext - Give any Large Language Model the power to interact with your ERPNext system through standardized tools and protocols.
Infrastructure that connects LLMs to ERPNext. Frappe Assistant Core works with the Model Context Protocol (MCP) to expose ERPNext functionality to any compatible Language Model, enabling:
Get up and running in 3 steps:
# 1. Get the app
cd frappe-bench
bench get-app https://github.com/buildswithpaul/Frappe_Assistant_Core
# 2. Install on your site
bench --site [site-name] install-app frappe_assistant_core
That's it! Your ERPNext system is now accessible to any MCP-compatible LLM.
Robust protocol handler that exposes ERPNext functionality through standardized tools.
Ready-to-use integrations including DXT file generation for Claude Desktop setup.
Document CRUD, search, reporting, analytics, Python execution, and visualization capabilities.
Comprehensive tool set for complete ERPNext integration
Extensible framework for custom tools, external app integration, and business-specific logic.
Professional admin interface for plugin management and configuration
Full OAuth 2.0 and OpenID Connect implementation with Dynamic Client Registration (RFC 7591), PKCE support, and standardized discovery endpoints for seamless integration with MCP Inspector and third-party tools.
Authentication, ERPNext permissions integration, audit logging, and role-based access.
Complete audit logging tracks all LLM interactions with your ERP data
Compatible with any MCP-enabled system - not locked to specific AI providers.
graph TB
subgraph "LLM Layer"
Claude[Claude Desktop]
GPT[GPT/Custom LLM]
API[LLM via API]
Future[Future LLMs]
end
subgraph "Integration Layer"
MCP[MCP Protocol<br/>JSON-RPC 2.0]
DXT[DXT...