erpnext-agent 1.0.1

ERPNext and Frappe REST/RPC MCP Server for Agentic AI!

Erpnext MCP

ERPNext and Frappe Framework enterprise resources planner. Built with the highest architectural standards, incorporating dynamic facades, custom API routing, and FastMCP tool decoration.

Documentation — Installation, deployment, usage across the MCP, API, and CLI interfaces, and guidance for provisioning the ERPNext / Frappe platform are maintained in the official documentation.

Table of Contents

• Overview
• Features
• Installation
• Usage
• Configuration
• MCP Tools
• Architecture
• Deployment
• Documentation
• Contributing
• License

---

Overview

Erpnext MCP provides a high-performance, model-optimized interface to Erpnext capabilities. It isolates the model from underlying API transport complexity, ensuring safe, idempotent, and highly traceable system interactions.

---

Features

• Dynamic Facade Orchestration: Integrates multi-inheritance clients cleanly under a single facade.
• Battle-Tested Resilience: Out-of-the-box credential authentication, connection polling, and request retry strategies.
• FastMCP Declarative Tools: Fast, native schema registration with full inline validation.
• Complete Test Intent Diversity: Deep, automated unit, integration, and mock tests ensuring high code coverage.

---

⚙️ Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
• Environment Variables: Define standard environment variables:
  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
• HTTP SSE Request Headers: Pass custom headers during transport initialization:
  • x-mcp-enabled-tools / x-mcp-disabled-tools
  • x-mcp-enabled-tags / x-mcp-disabled-tags
• HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
  • ?tools=tool1,tool2
  • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

---

Installation

Pick the extra that matches what you want to run:

Extra	Installs	Use when
erpnext-agent[mcp]	Slim MCP server only (agent-utilities[mcp] — FastMCP/FastAPI)	You only run the MCP server (smallest install / image)
erpnext-agent[agent]	Full agent runtime (agent-utilities[agent,logfire] — Pydantic AI + the epistemic-graph engine)	You run the integrated agent
erpnext-agent[all]	Everything (mcp + agent + logfire)	Development / both surfaces

# MCP server only (recommended for tool hosting — slim deps)
uv pip install "erpnext-agent[mcp]"

# Full agent runtime (Pydantic AI + epistemic-graph engine)
uv pip install "erpnext-agent[agent]"

# Everything (development)
uv pip install "erpnext-agent[all]"      # or: python -m pip install "erpnext-agent[all]"

Container images (:mcp vs :agent)

One multi-stage docker/Dockerfile builds two right-sized images, selected by --target:

Image tag	Build target	Contents	Entrypoint
knucklessg1/erpnext-agent:mcp	--target mcp	erpnext-agent[mcp] — slim, no engine/pydantic-ai/dspy/llama-index/tree-sitter	erpnext-mcp
knucklessg1/erpnext-agent:latest	--target agent (default)	erpnext-agent[agent] — full agent runtime + epistemic-graph engine	erpnext-agent

docker build --target mcp   -t knucklessg1/erpnext-agent:mcp    docker/   # slim MCP server
docker build --target agent -t knucklessg1/erpnext-agent:latest docker/   # full agent

Knowledge-graph database (epistemic-graph)

The full agent ([agent] / :latest) embeds the epistemic-graph engine (pulled in transitively via agent-utilities[agent]). For production — or to share one knowledge graph across multiple agents — run epistemic-graph as its own database container and point the agent at it instead of embedding it. Deployment recipes (single-node + Raft HA), connection config, and the full database architecture (with diagrams) are documented in the epistemic-graph deployment guide. The slim [mcp] server does not require the database.

---

Usage

You can launch the FastMCP server in stdio mode via Python module execution:

import asyncio
from erpnext_agent.mcp_server import get_mcp_instance

async def main():
    mcp = get_mcp_instance()
    # Execute stdio loop or launch server
    print("MCP Server ready.")

if __name__ == "__main__":
    asyncio.run(main())

For direct shell launch, execute:

python -m erpnext_agent.mcp_server

---

Configuration

The package is fully configurable via the environment variables listed below.

Connection & Credentials

Variable	Description	Default
ERPNEXT_URL	ERPNext / Frappe server endpoint URL (falls back to ERPNEXT_AGENT_BASE_URL)	http://localhost:8000
ERPNEXT_TOKEN	API token authentication (api_key:api_secret)	—
ERPNEXT_AGENT_BASE_URL	Endpoint URL fallback when ERPNEXT_URL is unset	—
ERPNEXT_AGENT_USERNAME	Username for password-based login	—
ERPNEXT_AGENT_PASSWORD	Password for password-based login	—
ERPNEXT_AGENT_SSL_VERIFY	TLS certificate verification	True

MCP server / transport

Variable	Description	Default
TRANSPORT	stdio, streamable-http, or sse	stdio
HOST	Bind host (HTTP transports)	0.0.0.0
PORT	Bind port (HTTP transports)	8000
MCP_TOOL_MODE	Tool surface: condensed, verbose, or both	condensed

Tool toggles

Each action-routed tool can be disabled individually via its toggle env var (set to false): AUTHENTICATIONTOOL, RESOURCETOOL (see the MCP Tools table above).

A local template is supplied inside .env.example. Copy this file as .env and fill out your specific service endpoint parameters before starting execution.

---

MCP Tools

Auto-generated from the live MCP server — do not edit by hand.

Condensed action-routed tools (default — MCP_TOOL_MODE=condensed)

MCP Tool	Toggle Env Var	Description
erpnext_agent_authentication	AUTHENTICATIONTOOL	Manage ERPNext Agent authentication operations.
erpnext_agent_resource	RESOURCETOOL	Manage ERPNext Agent resource operations.

Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)

13 per-operation tools — one per public API method (click to expand)

MCP Tool	Toggle Env Var	Description
erpnext_authGetLoggedUser	APITOOL	Alias for get_logged_user matching OpenAPI operationId.
erpnext_auth_get_logged_user	APITOOL	Snake-case alias for get_logged_user.
erpnext_call_method	APITOOL	Execute dotted path whitelisted RPC methods (covers 100% of custom functions).
erpnext_create_document	APITOOL	Create a new document resource.
erpnext_delete_document	APITOOL	Delete a specific document resource.
erpnext_get_document	APITOOL	Get a document resource by name.
erpnext_get_logged_user	APITOOL	Get the user that is logged in.
erpnext_get_version	APITOOL	Get installed app versions.
erpnext_list_documents	APITOOL	List document resources with pagination, filters, and selected fields.
erpnext_login	APITOOL	Authenticate yourself.
erpnext_logout	APITOOL	Logout from current session.
erpnext_update_document	APITOOL	Update a specific document resource.
erpnext_version	APITOOL	Alias for get_version.

2 action-routed tool(s) (default) · 13 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (condensed default · verbose 1:1 · both). Auto-generated — do not edit.

MCP Configuration Examples

Install the slim [mcp] extra. All examples install erpnext-agent[mcp] — the MCP-server extra that pulls only the FastMCP / FastAPI tooling (agent-utilities[mcp]). It deliberately excludes the heavy agent runtime (pydantic-ai, the epistemic-graph engine, dspy, llama-index), so uvx / container installs are far smaller. Use the full [agent] extra only when you need the integrated Pydantic AI agent.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "erpnext-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "erpnext-agent[mcp]",
        "erpnext-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "condensed",
        "AUTHENTICATIONTOOL": "True",
        "ERPNEXT_AGENT_BASE_URL": "http://localhost:8000",
        "ERPNEXT_AGENT_PASSWORD": "your_password",
        "ERPNEXT_AGENT_USERNAME": "your_username",
        "ERPNEXT_TOKEN": "your_api_key:your_api_secret",
        "ERPNEXT_URL": "http://localhost:8000",
        "RESOURCETOOL": "True"
      }
    }
  }
}

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "erpnext-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "erpnext-agent[mcp]",
        "erpnext-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "MCP_TOOL_MODE": "condensed",
        "AUTHENTICATIONTOOL": "True",
        "ERPNEXT_AGENT_BASE_URL": "http://localhost:8000",
        "ERPNEXT_AGENT_PASSWORD": "your_password",
        "ERPNEXT_AGENT_USERNAME": "your_username",
        "ERPNEXT_TOKEN": "your_api_key:your_api_secret",
        "ERPNEXT_URL": "http://localhost:8000",
        "RESOURCETOOL": "True"
      }
    }
  }
}

Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:

{
  "mcpServers": {
    "erpnext-mcp": {
      "url": "http://localhost:8000/erpnext-mcp/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name erpnext-mcp-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e HOST=0.0.0.0 \
  -e PORT=8000 \
  -e MCP_TOOL_MODE=condensed \
  -e AUTHENTICATIONTOOL=True \
  -e ERPNEXT_AGENT_BASE_URL=http://localhost:8000 \
  -e ERPNEXT_AGENT_PASSWORD=your_password \
  -e ERPNEXT_AGENT_USERNAME=your_username \
  -e ERPNEXT_TOKEN=your_api_key:your_api_secret \
  -e ERPNEXT_URL=http://localhost:8000 \
  -e RESOURCETOOL=True \
  knucklessg1/erpnext-agent:mcp

Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.

Additional Deployment Options

erpnext-agent can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

• Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
• Remote URL — connect to a server deployed behind Caddy at http://erpnext-mcp.arpa/mcp using the "url" key.

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

Page	Contents
Installation	pip, source, extras, prebuilt Docker image
Deployment	run the MCP and agent servers, Compose, Caddy + Technitium, env config
Usage	the MCP tools, the Api client, the CLI
Backing Platform	deploy ERPNext / Frappe with Docker
Overview	the dynamic facade and FastMCP tool layer
Concepts	concept registry (CONCEPT:ERPN-*)

AGENTS.md is the canonical contributor/agent guidance.

---

Contributing

Please audit all code changes against ecosystem guidelines in CONTRIBUTING.md if available, and run:

pre-commit run --all-files

---

License

This project is licensed under the MIT License. See the LICENSE file for complete details.

Deploy with agent-os-genesis

This package can be provisioned for you — skill-guided — by the agent-os-genesis universal skill (its single-package deploy mode): it picks your install method, seeds secrets to OpenBao/Vault (or .env), trusts your enterprise CA, registers the MCP server, and verifies it — the same machinery that stands up the whole Agent OS, narrowed to just this package. Ask your agent to "deploy erpnext-agent with agent-os-genesis".

Install mode	Command
Bare-metal, prod (PyPI)	uvx erpnext-mcp · or uv tool install erpnext-agent
Bare-metal, dev (editable)	uv pip install -e ".[all]" · or pip install -e ".[all]"
Container, prod	deploy knucklessg1/erpnext-agent:latest via docker-compose / swarm / podman / podman-compose / kubernetes
Container, dev (editable)	deploy docker/compose.dev.yml (source-mounted at /src; edits live on restart)

Secrets are read-existing + seeded via vault_sync — you are only prompted for what's missing.

Environment Variables

Package environment variables

Variable	Example	Description
HOST	0.0.0.0
PORT	8000
TRANSPORT	stdio	options: stdio, streamable-http, sse
ERPNEXT_URL	http://localhost:8000	ERPNext / Frappe server endpoint URL (falls back to ERPNEXT_AGENT_BASE_URL)
ERPNEXT_TOKEN	your_api_key:your_api_secret	API token authentication (api_key:api_secret)
ERPNEXT_AGENT_BASE_URL	http://localhost:8000	Endpoint URL fallback when ERPNEXT_URL is unset
ERPNEXT_AGENT_USERNAME	your_username	Username / password login (alternative to token auth)
ERPNEXT_AGENT_PASSWORD	your_password
ERPNEXT_AGENT_SSL_VERIFY	True
AUTHENTICATIONTOOL	True
RESOURCETOOL	True

Inherited agent-utilities variables (apply to every connector)

Variable	Example	Description
MCP_TOOL_MODE	condensed	Tool surface: condensed
MCP_ENABLED_TOOLS	—	Comma-separated tool allow-list
MCP_DISABLED_TOOLS	—	Comma-separated tool deny-list
MCP_ENABLED_TAGS	—	Comma-separated tag allow-list
MCP_DISABLED_TAGS	—	Comma-separated tag deny-list
EUNOMIA_TYPE	none	Authorization mode: none
EUNOMIA_POLICY_FILE	mcp_policies.json	Embedded Eunomia policy file
EUNOMIA_REMOTE_URL	—	Remote Eunomia authorization server URL
ENABLE_OTEL	False	Enable OpenTelemetry export
OTEL_EXPORTER_OTLP_ENDPOINT	—	OTLP collector endpoint
MCP_CLIENT_AUTH	—	Outbound MCP auth (oidc-client-credentials for fleet calls)
OIDC_CLIENT_ID	—	OIDC client id (service-account auth)
OIDC_CLIENT_SECRET	—	OIDC client secret (service-account auth)
DEBUG	False	Verbose logging
PYTHONUNBUFFERED	1	Unbuffered stdout (recommended in containers)
MCP_URL	http://localhost:8000/mcp	URL of the MCP server the agent connects to
PROVIDER	openai	LLM provider for the agent
MODEL_ID	gpt-4o	Model id for the agent
ENABLE_WEB_UI	True	Serve the AG-UI web interface

11 package + 19 inherited variable(s). Auto-generated from .env.example + the shared agent-utilities set — do not edit.