Connect AI assistants to your ERPNext instance via the Model Context Protocol (MCP) using the official Frappe API.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add erpnext -- node /path/to/erpnext-server/build/index.js~/.codex/config.toml
[mcp_servers.erpnext]
command = "node"
args = ["/path/to/erpnext-server/build/index.js"]
# codex mcp add erpnext -- node /path/to/erpnext-server/build/index.js~/.cursor/mcp.json
{
"mcpServers": {
"erpnext": {
"command": "node",
"args": [
"/path/to/erpnext-server/build/index.js"
]
}
}
}.vscode/mcp.json
{
"servers": {
"erpnext": {
"type": "stdio",
"command": "node",
"args": [
"/path/to/erpnext-server/build/index.js"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"erpnext": {
"command": "node",
"args": [
"/path/to/erpnext-server/build/index.js"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"erpnext": {
"command": "node",
"args": [
"/path/to/erpnext-server/build/index.js"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"erpnext": {
"command": "node",
"args": [
"/path/to/erpnext-server/build/index.js"
]
}
}
}