HiveDesk
MCP server that exposes an in-browser AI ERP (CRM, stock, invoices, HR) with role-aware agents, enabling natural language chat and confirm-before-write actions.
README
HiveDesk — Open Source AI ERP Desk (Frappe / ERPNext Ready)
HiveDesk is an open-source in-browser ERP with AI employee seats. Chat with sales, warehouse, purchase, accounts, HR, and ops agents. They read CRM, stock, and invoices — and ask before they write.
Built as a sandbox that can later point at a real Frappe / ERPNext site over REST + MCP.
Features
- AI seats — hire sales, warehouse, purchase, accounts, HR, ops, CEO, support, caller, WhatsApp
- ERP modules — CRM, Selling, Buying, Stock, Accounts, HR, Projects, Files
- Role-aware — a warehouse agent cannot post to payroll
- Confirm-before-write proposal cards
- MCP server at
GET/POST /api/mcp(JSON-RPC) for other agents - Mail + call transcripts in the sandbox
- Mobile-first amber PWA shell
Who it is for
- Teams evaluating AI inside ERPNext / Frappe
- Founders who want an open source ERP chatbot without standing up a bench first
- Developers building MCP tools against CRM and inventory
Quick start
git clone https://github.com/Akshit1018/S.HiveDesk.git
cd S.HiveDesk
npm install
VITE_AUTH_ENABLED=false npm run dev
Open http://127.0.0.1:8080.
This demo uses an in-browser ERP engine (PGLite). It is not a live Frappe site. Production swap notes live in docs/HANDOVER.md.
Tech stack
React 19 · TanStack Start · Vite · Tailwind · Zustand · PGLite · MCP JSON-RPC
License
Keywords
open source ERP, AI ERP assistant, ERPNext chatbot, Frappe AI agent, MCP ERP, in-browser ERP, inventory CRM HR desk, confirm-before-write agents
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.