freshcrate
Skin:/
Home > MCP Servers > Frappe_Assistant_Core

Frappe_Assistant_Core

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

Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

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

README

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.


🌟 What is Frappe Assistant Core?

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:

  • 🔌 LLM-Agnostic Integration: Works with Claude, GPT, custom models, or any MCP-compatible system
  • 📁 One-Click Claude Setup: Generate DXT files for instant Claude Desktop integration
  • 🔒 Enterprise Security: ERPNext permissions, audit logging, and role-based access control
  • 🛠️ 20+ Built-in Tools: Document operations, search, reporting, analytics, and visualization
  • 🚀 Plugin Architecture: Extensible framework for custom business logic and integrations
  • 🆓 Open Source: AGPL-3.0 licensed - transparent, community-driven development

⚡ Quick Installation

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.


🎯 Core Components

🔧 MCP Server Infrastructure

Robust protocol handler that exposes ERPNext functionality through standardized tools.

📦 Client Integration Packages

Ready-to-use integrations including DXT file generation for Claude Desktop setup.

🛠️ 21 Built-in Tools

Document CRUD, search, reporting, analytics, Python execution, and visualization capabilities.

Available Tools Comprehensive tool set for complete ERPNext integration

🔌 Plugin Architecture

Extensible framework for custom tools, external app integration, and business-specific logic.

Admin Interface Professional admin interface for plugin management and configuration

🔐 OAuth 2.0 / OIDC Authentication

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.

🔒 Enterprise Security Layer

Authentication, ERPNext permissions integration, audit logging, and role-based access.

Audit Trail Complete audit logging tracks all LLM interactions with your ERP data

🌐 LLM-Agnostic Design

Compatible with any MCP-enabled system - not locked to specific AI providers.

Architecture Overview

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 File Generator<br/>One-Click Setup]
        Bridge[STDIO Bridge]
    end

    subgraph "Frappe Assistant Core"
        Server[MCP Server<br/>API Handler]
        Registry[Tool Registry<br/>20+ Tools]
        
        subgraph "Plugin System"
            CorePlugin[Core Plugin<br/>Always Enabled]
            DataSci[Data Science<br/>Plugin]
            Viz[Visualization<br/>Plugin]
            Custom[Custom<br/>Plugins]
        end
        
        Security[Security Layer<br/>Auth & Permissions]
        Audit[Audit Trail<br/>Logging System]
    end

    subgraph "ERPNext/Frappe"
        Database[(ERPNext<br/>Database)]
        Docs[Documents<br/>Customers, Sales, etc.]
        Reports[Reports<br/>Analytics]
        Workflows[Workflows<br/>Business Logic]
    end

    %% Connections
    Claude --> MCP
    GPT --> MCP
    API --> MCP
    Future --> MCP
    
    Claude -.->|One-Click| DXT
    DXT --> Bridge
    Bridge --> Server
    
    MCP --> Server
    Server --> Registry
    Registry --> CorePlugin
    Registry --> DataSci
    Registry --> Viz
    Registry --> Custom
    
    Server --> Security
    Server --> Audit
    
    CorePlugin --> Database
    DataSci --> Database
    Viz --> Database
    Custom --> Database
    
    Database --> Docs
    Database --> Reports
    Database --> Workflows

    %% Styling
    classDef llm fill:#e1f5fe,stroke:#0277bd,stroke-width:2px
    classDef integration fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef core fill:#e8f5e8,stroke:#2e7d32,stroke-width:2px
    classDef plugin fill:#fff3e0,stroke:#f57c00,stroke-width:2px
    classDef erp fill:#fce4ec,stroke:#c2185b,stroke-width:2px

    class Claude,GPT,API,Future llm
    class MCP,DXT,Bridge integration
    class Server,Registry,Security,Audit core
    class CorePlugin,DataSci,Viz,Custom plugin
    class Database,Docs,Reports,Workflows erp
Loading

Data Flow Architecture

sequenceDiagram
    participant U as User
    participant C as Claude/LLM
    participant M as MCP Server
    participant T as Tool Registry  
    participant P as Plugin
    participant E as ERPNext DB

    U->>C: "Create customer Acme Corp"
    C->>M: MCP Request: create_document
    M->>T: Get tool: create_document
    T->>P: Execute Core Plugin Tool
    P->>E: frappe.get_doc().insert()
    E-->>P: Document Created
    P-->>T: Success Response
    T-->>M: Tool Result
    M-->>C: MCP Response
    C-->>U: "Customer created successfully"
    
    Note over M,E: All operations logged in audit trail
    Note over M: Security & permissions enforced
Loading

Plugin Architecture Detail

graph LR
    subgraph "External Apps"
        App1[Custom Frappe App]
        App2[Industry-Specific App]
        App3[Third-Party App]
    end
    
    subgraph "Tool Discovery"
        Hooks[hooks.py<br/>assistant_tools]
        Scanner[Plugin Scanner]
        Registry[Tool Registry]
    end
    
    subgraph "Core Plugins"
        CoreP[Core Plugin<br/>Document Operations]
        DataP[Data Science Plugin<br/>Python Execution]
        VizP[Visualization Plugin<br/>Charts & Dashboards]
    end
    
    subgraph "Runtime Management"
        Manager[Plugin Manager]
        Config[Plugin Configuration]
        State[Enable/Disable State]
    end

    App1 --> Hooks
    App2 --> Hooks  
    App3 --> Hooks
    
    Hooks --> Scanner
    Scanner --> Registry
    
    CoreP --> Registry
    DataP --> Registry
    VizP --> Registry
    
    Registry --> Manager
    Manager --> Config
    Manager --> State

    classDef external fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef discovery fill:#f1f8e9,stroke:#388e3c,stroke-width:2px
    classDef plugins fill:#fff8e1,stroke:#f57f17,stroke-width:2px
    classDef management fill:#fce4ec,stroke:#c2185b,stroke-width:2px

    class App1,App2,App3 external
    class Hooks,Scanner,Registry discovery
    class CoreP,DataP,VizP plugins
    class Manager,Config,State management
Loading

Security & Permissions Flow

graph TD
    Request[LLM Request] --> Auth{Authenticated?}
    Auth -->|No| Reject[Reject Request]
    Auth -->|Yes| UserCheck{User Enabled?}
    UserCheck -->|No| Reject
    UserCheck -->|Yes| RoleCheck{Has Assistant Role?}
    RoleCheck -->|No| Reject
    RoleCheck -->|Yes| ToolPerm{Tool Allowed?}
    ToolPerm -->|No| Reject
    ToolPerm -->|Yes| DocPerm{ERPNext Permissions?}
    DocPerm -->|No| Reject
    DocPerm -->|Yes| Execute[Execute Tool]
    Execute --> AuditLog[Log to Audit Trail]
    Execute --> Response[Return Response]

    classDef security fill:#ffebee,stroke:#d32f2f,stroke-width:2px
    classDef success fill:#e8f5e8,stroke:#2e7d32,stroke-width:2px
    classDef reject fill:#fafafa,stroke:#757575,stroke-width:2px

    class Auth,UserCheck,RoleCheck,ToolPerm,DocPerm security
    class Execute,AuditLog,Response success
    class Reject reject
Loading

Integration Patterns

graph LR
    subgraph "Pattern 1: Direct Claude Desktop"
        CD[Claude Desktop]
        DXT[DXT File]
        STDIO[STDIO Bridge]
        CD --> DXT --> STDIO
    end
    
    subgraph "Pattern 2: API Integration"
        CustomLLM[Custom LLM App]
        HTTP[HTTP API]
        MCP_API[MCP Endpoint]
        CustomLLM --> HTTP --> MCP_API
    end
    
    subgraph "Pattern 3: Webhook/Event"
        External[External System]
        Webhook[Webhook Endpoint]
        Queue[Background Queue]
        External --> Webhook --> Queue
    end
    
    subgraph "Frappe Assistant Core"
        Core[MCP Server]
    end
    
    STDIO --> Core
    MCP_API --> Core
    Queue --> Core

    classDef pattern1 fill:#e3f2fd,stroke:#1565c0,stroke-width:2px
    classDef pattern2 fill:#e8f5e8,stroke:#2e7d32,stroke-width:2px  
    classDef pattern3 fill:#fff3e0,stroke:#f57c00,stroke-width:2px
    classDef core fill:#fce4ec,stroke:#c2185b,stroke-width:2px

    class CD,DXT,STDIO pattern1
    class CustomLLM,HTTP,MCP_API pattern2
    class External,Webhook,Queue pattern3
    class Core core
Loading

Plugin-based architecture supports any MCP-compatible LLM


🚀 Getting Started

Ready to connect your LLM to ERPNext? Follow these simple steps:

Step 1: Get Your MCP Endpoint URL

  1. Open FAC Admin Page

    • After installation, go to: Desk → Tools → FAC Admin
    • Or navigate directly to: https://your-site.com/app/fac-admin
  2. Copy Your MCP Endpoint

    • On the FAC Admin page, you'll see your MCP Endpoint URL
    • It looks like: https://your-site.com/api/method/frappe_assistant_core.api.fac_endpoint.handle_mcp
    • Copy this URL - you'll need it in the next step

FAC Admin Page Get your MCP endpoint URL from the FAC Admin page

Step 2: Add MCP Server to Your LLM

Choose your LLM platform and follow the instructions:

🔷 Claude Desktop (Recommended)

  1. In Claude Desktop, click the settings icon (⚙️) in the bottom left
  2. Click "Connectors"
  3. Click "+ Add Custom Connector"" button
  4. Fill in the details:
    • Name: Frappe Assistant Core (or any name you prefer)
    • URL: Paste your MCP endpoint URL from Step 1
  5. Click "Add"

Claude Add Server

🟢 ChatGPT (Plus Users Only)

Note: Custom connectors are only available for ChatGPT Plus and above plan users with Developer Mode enabled

  1. In ChatGPT, open the side panel
  2. Go to Connectors menu
  3. Click "Create" button
  4. Fill in the connector details:
    • Name: Frappe Assistant Core (or any name you prefer)
    • URL: Paste your MCP endpoint URL from Step 1
  5. Click "Create"

ChatGPT Connector

🌐 Claude Web (claude.ai)

  1. On Claude Web, click your profile icon
  2. Go to Settings → Integrations
  3. Click "Add Custom Connector"
  4. Fill in:
    • Name: Frappe Assistant
    • URL: Paste your MCP endpoint URL from Step 1
  5. Click "Add"

Step 3: Authenticate & Connect

  1. Click "Connect" in your LLM client
  2. You'll be redirected to your Frappe login page
  3. Login with your Frappe username and password
  4. Click "Authenticate" to authorize the LLM to access your ERPNext data
  5. Done! You'll be redirected back to your LLM

OAuth Flow Secure OAuth 2.0 authentication - login once, access anytime

Step 4: Start Using Your Tools!

Your LLM can now access ERPNext! Try these commands:

"List all customers in the system"

"Create a new customer called Acme Corp with email test@acme.com"

"Show me this month's sales report"

"What are the top 5 selling items?"


🧪 For Developers: MCP Inspector Testing

Want to test and debug your MCP server? Use the MCP Inspector tool:

1. Enable CORS for Local Testing

Add to your site_config.json:

{
  "oauth_cors_allowed_origins": "*"
}

Or in Assistant Core Settings → OAuth tab → Allowed Public Client Origins: http://localhost:6274

2. Open MCP Inspector

  • Go to: http://localhost:6274/
  • Select "Streamable HTTP" transport
  • Enter your MCP Endpoint URL from FAC Admin
  • Click "Guided OAuth Flow" and click Continue for each step
  • Login when prompted

3. Test Tools

  • Browse available tools
  • Execute test calls
  • Debug request/response data
  • Monitor OAuth token flow

MCP Inspector MCP Inspector provides visual testing and debugging for developers


📚 Advanced Integration

For custom applications, advanced OAuth flows, or programmatic integration, see our comprehensive guides:


📚 Documentation

📖 Complete Documentation Index - Browse all documentation organized by category

🚀 Quick Start Guides

Guide Description
Getting Started Complete setup guide for new users
Claude Desktop Quick Start Connect Claude Desktop in 5 minutes
Migration Guide New! Migrate from STDIO to OAuth
OAuth Quick Start OAuth 2.0 setup in 2 minutes

🏗️ Architecture & Technical

Guide Description
Architecture Overview System design and plugin architecture
MCP StreamableHTTP Guide New! OAuth + StreamableHTTP integration
Technical Documentation Complete technical reference
Performance Guide Optimization and monitoring

📖 API Reference

Guide Description
API Reference MCP protocol endpoints and OAuth APIs
Tool Reference Complete catalog of all 21 available tools
OAuth Setup Guide Comprehensive OAuth configuration

🛠️ Development

Guide Description
Development Guide Create custom tools and plugins
External App Development Tools in your Frappe apps (recommended)
Plugin Development Build internal plugins
Test Case Creation Testing patterns and best practices

🏢 Integration Scenarios

  • Business Users + Claude: Natural language ERP operations through Claude Desktop
  • Developers + Custom LLMs: Build AI-powered business applications with ERPNext data
  • System Integrators: Deploy LLM-ERP solutions for clients across industries
  • AI Companies: Add ERPNext capabilities to existing AI products and services
  • Enterprise Teams: Create department-specific AI tools with custom plugins

🌟 Why Choose Frappe Assistant Core?

LLM-Agnostic - Not locked to any specific AI provider or model
Production Ready - Enterprise-grade security, permissions, and audit logging
One-Click Setup - DXT file generation for instant Claude Desktop integration
20+ Built-in Tools - Comprehensive ERPNext functionality out of the box
Plugin Architecture - Unlimited extensibility for custom business logic
Open Source - AGPL-3.0 licensed with transparent, community-driven development


🤝 Contributing

We welcome contributions! This is an open source project under AGPL-3.0.

  1. Fork the repository
  2. Create a feature branch
  3. Add tests for new functionality
  4. Submit a pull request

See Contributing Guidelines for detailed instructions.


📄 License & Support

License: AGPL-3.0 - Free for commercial use with source code transparency

Community Support: GitHub Issues and Discussions

Enterprise Support: Need custom development or priority support? Contact us at jypaulclinton@gmail.com


🚀 Ready to give LLMs access to your ERPNext data? Get started now!

Built with ❤️ by the community, for developers and businesses integrating AI with ERP systems.

Release History

VersionChangesUrgencyDate
v2.4.3## [2.4.3](https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.4.2...v2.4.3) (2026-05-14) ### Bug Fixes * accept JSON-string roles in update_tool_role_access ([e8d391c](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/e8d391c773764335ef04b0ac8bd3645b97e45121)) * accept JSON-string roles in update_tool_role_access ([b001769](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/b0017692a5b742ad7a029030328cc3ca54491bfe)) * add blank line after import for ruHigh5/14/2026
v2.4.2## [2.4.2](https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.4.1...v2.4.2) (2026-05-07) ### Bug Fixes * accept JSON-string roles in update_tool_role_access ([e99eff5](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/e99eff59db815cfe06982f9d43136a10e4aa3bf5)) * **audit-log:** preserve token-count fields in sanitized output ([fbcce43](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/fbcce431472b21d270d215cb9113c47fea3f32e8)) * **ci:** pin commitlint High5/7/2026
v2.4.1## [2.4.1](https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.4.0...v2.4.1) (2026-04-23) ### Bug Fixes * repair HRMS Skill link corruption from v2.4.0 rename patch ([4f043ac](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/4f043ac7071dde8137ba568d1a437e47c61c1579)) * repair HRMS Skill link corruption from v2.4.0 rename patch ([#153](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/153)) ([973c2e7](https://github.com/buildswithpaul/Frappe_Assistant_High4/23/2026
v2.4.0# [2.4.0](https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.3.4...v2.4.0) (2026-04-17) ### Bug Fixes * drop unused visualization libs from run_python_code sandbox ([#146](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/146)) ([6a002da](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/6a002da619c8cb206e5e5a48a5ae838fc40a545c)) * enforce parent document permission check in extract_file_content ([bd88d75](https://github.com/buildswithpaul/Frappe_AssiHigh4/17/2026
v2.3.4## [2.3.4](https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.3.3...v2.3.4) (2026-04-07) ### Bug Fixes * prevent OAuth Basic auth monkey-patch from persisting across worker requests ([#131](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/131)) ([5c22232](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/5c22232721d3bd4c34ec15014c60a490a44803ed)), closes [#129](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/129) High4/7/2026
v2.3.3## [2.3.3](https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.3.2...v2.3.3) (2026-03-19) ### Bug Fixes * make PaddleOCR dependencies optional for Frappe v16 ([#118](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/118)) ([#121](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/121)) ([a2f493e](https://github.com/buildswithpaul/Frappe_Assistant_Core/commit/a2f493ea6c207ca59d351d88faf4f0e8e90995bb)) Low3/19/2026
v2.3.2### 🆕 New — OCR & Document Extraction FAC now supports extracting text from images and scanned PDFs directly through your AI assistant. Two backends are available out of the box: - **PaddleOCR integration** — high-accuracy text extraction using PaddleOCR with support for multiple languages. Runs in a subprocess with configurable memory limits and timeouts to keep your server stable. - **Vision model support** — use Ollama-based vision models (e.g., `deepseek-ocr:latest`) as an alternativLow3/18/2026
v2.3.1> Database-backed plugin & tool management with Frappe V16 support ## What's New This release introduces a robust, database-backed system for managing plugin and tool enable/disable states and access control. It replaces the previous JSON-based approach with new DocTypes for granular, atomic, and multi-worker-safe configuration. Frappe V16 is now officially supported. --- ### Plugin & Tool Management Architecture #### FAC Plugin Configuration DocType A new DocType for atomic, datLow2/6/2026
v2.3.0# Frappe Assistant Core v2.3.0 ## Highlights **Prompt Templates System** - This release introduces a major new feature: database-driven prompt templates with full MCP protocol support. Domain experts can now create reusable, parameterized prompts that users can customize and execute via AI clients. --- ## Major Feature - Prompt Templates System ### MCP Prompts Support FAC now supports the MCP `prompts/list` and `prompts/get` protocol methods, enabling "Prompt Engineering as a SerLow1/9/2026
v2.2.2### 🏢 Repository Migration & Rebranding #### GitHub Repository Update - **Migrated** repository from `clinu/Frappe_Assistant_Core` to `buildswithpaul/Frappe_Assistant_Core` - **Updated** all documentation links, URLs, and references across the project - **Updated** manifest.json, README.md, BUILD.md, and configuration files - **Maintained** backwards compatibility - existing installations continue to work ### 🚀 Enhanced #### OAuth 2.0 Client Registration Enhancements - **Fixed** Low12/3/2025
v2.2.1### 🚀 Enhanced #### Prepared Report Polling Support - [Issue 52](https://github.com/buildswithpaul/Frappe_Assistant_Core/issues/52) - **Implemented** automatic polling logic for prepared (background) reports - **Added** exponential backoff strategy (2→4→6→9→13 seconds) to efficiently wait for report completion - **Enabled** seamless UX where AI gets report data without interrupting conversation flow - **Eliminated** manual retry requests - system automatically polls until report is readyLow11/24/2025
v2.2.0**Release Date:** October 13, 2025 ## 🎯 What's New Frappe Assistant Core has been completely rebuilt with **StreamableHTTP transport and OAuth 2.0 authentication**, making it compatible with modern MCP clients including **Claude Web** and browser-based tools. ### Key Highlights ✅ **OAuth 2.0 Security** \- Industry-standard authentication replacing API keys ✅ **Web Client Support** \- Works with Claude Web, MCP Inspector, and browser tools ✅ **Simpler Deployment** \- HTTP endpoinLow10/14/2025
v2.1.1**Released:** September 2025 ## What's New **CI/CD Pipeline** Added proper GitHub Actions workflows for automated testing and linting. **SSE Bridge Improvements** - New admin dashboard with real-time status monitoring - One-click start/stop controls - Better error handling when dependencies are missing **Better Tool Error Handling** Improved error messages and logging in tool execution. You'll now get clearer feedback when something goes wrong instead of cryptic errors. **DLow9/22/2025
v2.1.0**Major Performance & Feature Release** - August 2025 --- ## What's New ### 📄 File Processing & Data Science Plugin - **New Tool**: `extract_file_content` - Extract text from PDF, images (OCR), Excel, and Word documents - **LLM-Optimized**: Content formatted for AI analysis with structure preservation ### ⚙️ Admin Interface Improvements - **Revamped UI**: Cleaner interface for Assistant Admin page and settings - **Real-time Status**: Live plugin monitoring and configuration vaLow8/29/2025
v2.0.3**Release Date:** 08 August 2025 **Version:** 2.0.3 **Security Focus:** Enterprise-grade security enhancements and tool improvements ## 🔒 Major Security Enhancements ### Python Code Execution Security - **🛡️ Read-Only Database Wrapper**: Implemented comprehensive read-only database access preventing all dangerous SQL operations (DELETE, UPDATE, INSERT, DROP, ALTER, CREATE, TRUNCATE) - **👤 Secure User Context Management**: Added proper user context handling with automatic rollbacLow8/7/2025
v2.0.2## What's Changed * Hotfix for the issue faced during the frappe cloud installation by @buildswithpaul in https://github.com/buildswithpaul/Frappe_Assistant_Core/pull/22 * Bumped up the version and updated the documents by @buildswithpaul in https://github.com/buildswithpaul/Frappe_Assistant_Core/pull/23 **Full Changelog**: https://github.com/buildswithpaul/Frappe_Assistant_Core/compare/v2.0.1...v2.0.2Low7/28/2025
v2.0.1**Release Date**: July 26, 2025 **Version**: 2.0.1 **Type**: Major Bug Fixes & Tool Improvements ## 🎯 Overview Version 2.0.1 is a significant maintenance release that addresses critical issues in document creation, dashboard chart functionality, and custom tool discovery. This release dramatically improves the reliability and usability of AI assistant tools for Frappe Framework. ## 🚀 Major Improvements ### 📋 Document Creation Tool Overhaul **Problem Solved**: The `create_Low7/26/2025
v2.0.0**Release Date**: July 22, 2025 **License**: AGPL-3.0 (changed from MIT) **Breaking Changes**: Yes ### 🌟 Release Highlights This major release transforms Frappe Assistant Core into a fully extensible, plugin-based platform with enhanced visualization capabilities and stronger open source protection through AGPL-3.0 licensing. --- ## 🚀 New Features ### 🏗️ **Plugin-Based Architecture** - **Custom Tool Development**: Create your own tools using the new plugin system - **Low7/22/2025
v1.3.0# Release Notes - Frappe Assistant Core v1.3.0 ## 🔒 Security & Reliability Release This release focuses on comprehensive security enhancements and code refactoring to ensure robust, secure AI assistant operations within Frappe Framework environments. ### 🔐 Security Enhancements #### Multi-Layer Security Framework - **Role-Based Access Control**: Implemented comprehensive role-based tool access with `System Manager`, `Assistant Admin`, `Assistant User`, and `Default` user categorieLow7/14/2025
v1.2.0**Release Date**: July 4, 2025 **Type**: Major Feature Release **Compatibility**: ✅ Full backward compatibility ## 🎉 **What's New in v1.2.0** This release transforms Claude for Frappe ERP from a functional extension into a **production-ready, professionally documented, and developer-friendly platform**. We've completely redesigned the architecture with a **plugin-based system**, added comprehensive build tools, fixed critical data handling issues, and created extensive documentationLow7/4/2025
v1.1.1## 🐛 Bug Fixes ### Fixed Critical Installation Issue with `bench get-app` - **Issue**: Users were unable to auto-install the app using the `bench get-app` command - **Root Cause**: App name contained hyphens (`-`) which caused compatibility issues with Frappe's installation process - **Solution**: - Renamed app to use underscores (`_`) instead of hyphens - Removed unnecessary `setup.py` file that was causing conflicts ## 💥 Breaking Changes ⚠️ **App Name Change**: If you haveLow7/3/2025
v1.1.0# 🚀 Release v1.1.0 - Major Architecture Enhancement We're excited to announce the release of v1.1.0, featuring significant architectural improvements, WebSocket support, advanced caching, and comprehensive testing infrastructure. This release transforms the MCP Frappe integration into a production-ready solution with enterprise-grade features. ## ✨ Major Features ### 🌐 WebSocket MCP Server Integration - **Real-time Communication**: WebSocket-based MCP server with persistent connectioLow6/30/2025
v1.0.1## 🚀 Features ### Automatic Artifact Streaming System **Implement comprehensive artifact streaming for all tools** We've introduced an intelligent artifact streaming system that significantly improves handling of large tool results and enhances user experience: **Key Improvements:** - **Smart Detection**: Automatically detects large results (>5 lines or >1000 characters) and streams them appropriately - **Tool Categorization**: Intelligent categorization system for different tool tyLow6/28/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

pydantic-deepagentsPython Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and0.3.24
telegram-mcp🤖 Manage multiple Telegram accounts effortlessly with AI-driven tools for bulk messaging, scheduling, and more in one easy-to-use platform.main@2026-06-07
AIDomesticCoreAIJ🛠️ Build a robust AI Kernel for stable, auditable, and sovereign AI systems, ensuring secure execution and compliance across various domains.main@2026-06-07
mcp-agent-framework🤖 Orchestrate AI agents at scale using the MCP framework, enabling seamless context sharing, communication, and integration for enhanced collaboration.master@2026-06-07
AntigravityMobile📱 Monitor your AI conversations and model quotas effortlessly with Antigravity Mobile, a mobile-friendly dashboard for Antigravity IDE.master@2026-06-07

More in MCP Servers

agentroveYour own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.
node9-proxyThe Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
mcp-compressorAn MCP server wrapper for reducing tokens consumed by MCP tools.
claude-plugins-officialOfficial, Anthropic-managed directory of high quality Claude Code Plugins.