mcp-erp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-erp-server Which of Northwind's orders are still open, and do we have stock to ship them?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-erp-server
A Model Context Protocol server that lets AI assistants query an ERP — with per-department access, provenance on every answer, and read-only by default.
Connecting an assistant to company systems is easy. Connecting it safely is the real work: a sales rep should not be able to ask about payables, a director should be able to read everything without being able to change anything, and every number the assistant repeats should be traceable to where it came from.
This server shows that pattern over a small synthetic ERP (sales, procurement, finance, inventory).
$ ERP_PROFILE=buyer npm start
mcp-erp-server running for profile "buyer"
tools: procurement_open_orders, inventory_stock ← nothing from sales or financeThree rules
flowchart LR
A[AI assistant] -->|MCP| S[mcp-erp-server]
P[Access profile<br/>per department:<br/>none / read / write] --> S
S -->|registers only<br/>allowed tools| T[Tools]
T --> D[(ERP adapters)]
T -->|data + provenance| A1. Access by profile — at registration time.
Each person has a profile with a level per department (none, read, write). Tools for departments they can't use are never registered, so the assistant doesn't even know they exist for that person. That is stronger than refusing at call time: there is no tool name to probe and nothing to talk the model into.
Profile | sales | procurement | finance | inventory |
| read | read | read | read |
| write | – | read | read |
| read | – | – | read |
| – | read | – | read |
2. Provenance on every answer. Every response is an envelope with the data and where it came from:
{
"data": [ { "id": "SO-1001", "status": "confirmed", "total": 3900 } ],
"provenance": {
"source": "sales.orders",
"filters": { "status": "confirmed", "limit": 20 },
"records": 1,
"queried_at": "2026-11-18T12:00:00.000Z",
"profile": "sales_rep"
}
}The assistant can cite it, and a person can check it. A number without a source is not an answer.
3. Read-only by default; writes are explicit.
There is one write tool, sales_update_order_status. It exists only for profiles with write on sales, it accepts only valid status transitions (quote → confirmed → invoiced → shipped, or cancelled before invoicing), and without confirm: true it returns a dry-run preview of the change instead of making it. Repeating a write that is already in place changes nothing.
Related MCP server: MCP4Acumatica
Tools
Tool | Department | What it answers |
| sales · read | Find a customer by name, id or tax id |
| sales · read | Orders by status / customer, with computed totals |
| sales · read | Tier price for a customer, and whether it is under the floor price |
| sales · write | Move an order to a new status (dry run unless |
| procurement · read | Purchase orders not fully received, pending quantity per line |
| finance · read | Open / overdue invoices and the total |
| inventory · read | On-hand, reserved, available and shortages per location |
Use it with Claude Desktop (or any MCP client)
{
"mcpServers": {
"erp": {
"command": "npx",
"args": ["tsx", "/path/to/mcp-erp-server/src/index.ts"],
"env": { "ERP_PROFILE": "sales_rep" }
}
}
}Then ask things like "Which of Northwind's orders are still open, and do we have stock to ship them?" — the assistant chains sales_find_customer → sales_list_orders → inventory_stock, and every figure in its answer carries its source.
Run it
npm install
npm test # 19 tests, end to end through a real MCP client
ERP_PROFILE=director npm start # stdio serverProject layout
src/access.ts profiles and the can(profile, department, level) check
src/data.ts synthetic ERP data (swap for adapters over real systems)
src/server.ts tool registration per profile, provenance envelope, the write gate
src/index.ts stdio entry point (profile from ERP_PROFILE)
test/ 19 tests using the MCP SDK's in-memory client/server pairContext
A generic, clean-room implementation of a pattern for giving AI assistants safe access to business systems: scoped by role, explicit about where every number comes from, and unable to change data without confirmation. All names and data here are synthetic.
MIT licensed.
Available Tools
6 toolsfinance_receivablesReceivablesCRead-only
Open and overdue invoices, with totals.
Inputs: onlyOverdue.
inventory_stockStock levelsCRead-only
On-hand, reserved and available quantity per product and location.
Inputs: sku, location.
sales_find_customerFind customerBRead-only
Search customers by name, id or tax id. Returns tier and city.
Inputs: query (required).
sales_get_priceGet price for a customerCRead-only
Price of a product for a customer's tier, and whether it is above the floor price.
Inputs: sku (required), customerId (required).
sales_list_ordersList sales ordersBRead-only
List sales orders, optionally filtered by status and customer. Totals are computed from the lines.
Inputs: limit, status, customerId.
sales_update_order_statusUpdate sales order statusAIdempotent
Move a sales order to a new status. Without confirm=true this only returns a preview (dry run). Only valid transitions are accepted.
Inputs: status (required), orderId (required), confirm.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct resource and action: customer lookup, order listing, price lookup, order status transition, receivables, and stock levels. No two tools could plausibly be confused for one another, and the domain prefixes further separate sales, finance, and inventory concerns.
The pattern is namespace_verb_noun (sales_find_customer, sales_list_orders, sales_update_order_status), applied consistently within the sales namespace. The finance_receivables and inventory_stock tools drop the verb and read as nouns, a minor but noticeable deviation from the rest of the set.
Six tools is a lean, well-scoped surface where each tool maps to a clear question an ERP assistant would ask. It is on the thin side for a system as broad as an ERP, but nothing feels padded or redundant.
The set covers read paths for customers, orders, pricing, receivables, and stock, plus one guarded write (order status). However, there is no order creation, no customer or inventory write operations, and no invoice or line-item detail retrieval, leaving notable gaps for a full ERP lifecycle.
Maintenance
Related MCP Connectors
Company and industrial data for AI assistants: datasets, SQL, dashboards, alarms, with approvals.
Read-only finance and operations controls for AI agents with evidence and safe next actions.
Connect assistants to your company tools with per-person, per-action grants and a full audit log.
Read, write and run Odoo actions from any AI app, as each user, with approval rules per colleague.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables comprehensive interaction with ERPNext systems through natural language, providing secure access to any document type (customers, items, invoices, etc.) with enterprise-grade permission controls and audit logging.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to securely access and interact with Acumatica ERP data using per-user OAuth, role-based permissions, and automatic redaction of sensitive fields.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to access and query ERP data—sales, invoices, payables/receivables, cash flow, inventory, suppliers, and financial records—through natural language, using an authorized session capture login.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to securely access and interact with Odoo data through natural language, supporting CRUD operations, attachments, and role-based permissions.-