Frappe Assistant Core
Talk to your ERPNext site. FAC lets Claude, ChatGPT, and other MCP-ready LLMs work directly with your invoices, customers, stock, workflows, and custom apps — inside your ERPNext permissions, with every call logged.
エージェントを強化
公開元からインストールします。PlugMCP のエンドポイントではありません。
リモート URL か、手元のマシンのコマンドか 2 つのインストール方法の違い
PlugMCP で実行
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
起動公開元より
Talk to your ERPNext site. FAC lets Claude, ChatGPT, and other MCP-ready LLMs work directly with your invoices, customers, stock, workflows, and custom apps — inside your ERPNext permissions, with every call logged.
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
FAC 3.0 introduces FAC Chat — an opt-in, in-Frappe AI chat assistant powered by FAC Cloud, our managed service. What it does, what it costs and how to sign up: https://fac-suite.com.
FAC now offers two ways to use it:
/copilot,
powered exclusively by FAC Cloud. One subscription covers LLM
access across providers, conversation memory, RAG, and workflow
automation. Ships disabled by default. See
https://fac-suite.com.The split is intentional: BYO-LLM keeps the existing free MCP path untouched; FAC Chat is the managed experience for teams that want the chat inside Frappe without wiring up their own LLM keys. See FAC Chat below for full details.
Once FAC is installed, your team can ask an LLM for things they'd normally do by hand:
"Show me overdue invoices from our top five customers."
"Update this lead's status to Qualified and set next action date to Monday."
"Run the monthly revenue report and summarise the top movers."
"How much stock of SKU-1234 do we have across all warehouses?"
Behind that simple interaction, FAC exposes 24 built-in tools for the things your team does every day — document CRUD, search, reports, workflows, analytics, file extraction, and dashboards. Admins can publish Skills (reusable instructions that teach the LLM how to handle a specific job) and Prompt Templates (saved starting points users can pick from the admin UI) so answers stay consistent and use the right reports. The LLM authenticates over OAuth 2.0 as a real ERPNext user, so it only sees data that user can already see in the desk. Every call is recorded in the Assistant Audit Log.
It's a Frappe app, so developers can extend the toolset from their own Frappe apps through a hook — your data model, your business logic, scoped per your app.
Your data stays in your site. You control which LLM connects.
Two install paths depending on how you run Frappe.
cd frappe-bench
bench get-app https://github.com/buildswithpaul/Frappe_Assistant_Core
bench --site <your-site> install-app frappe_assistant_core
Node 22.12+ is needed only to build the FAC Chat UI. The assets are
built on your instance rather than shipped pre-built, so a bench on an
older Node will fail that build step. Upgrade Node to 22.12 or newer and re-run
bench build. A site using FAC purely as an MCP server does not need
this.
Requires Frappe v15 or v16 and Python 3.10+.
Once installed, the same four steps work for any MCP-compatible client. Example shown for Claude Desktop:
For ChatGPT, Claude Web, and MCP Inspector walkthroughs, see the Quick Start on the docs site.
FAC Chat is an opt-in, SaaS-powered chat experience that ships inside
FAC. Where the MCP server lets external LLM clients (Claude Desktop,
Cursor, ChatGPT desktop) talk to your Frappe data with your own LLM
keys, FAC Chat brings the conversation inside Frappe itself — a widget
on every Desk page and a full-screen SPA at /copilot — powered by a
FAC Cloud subscription.
Plans, pricing and sign-up live at https://fac-suite.com; this section covers only what the app itself does.
These are mutually exclusive at the chat layer: the in-Frappe chat UI is only available through FAC Cloud. There is no BYO-LLM path for FAC Chat — if you want to bring your own LLM, use the MCP server.
Both options share the same plugin registry, the same
Assistant Audit Log, and the same OAuth-based authentication.
Enabling FAC Chat does NOT change anything for your MCP clients — both
can run side by side.
That is the whole thing — no bench restart. The chat hooks are
registered unconditionally and every consumer checks the toggle at
request time, so other workers pick up the new state on their next
request.
A discovery banner on the Desk landing page will also walk admins through enabling chat — it appears once per admin and can be dismissed.
After enabling:
/copilot.FAC gives you two ways to shape what the LLM does with your data.
Skills are reusable instructions you give the LLM — stored as
FAC Skill documents inside your site. Each skill has a skill_id,
a description, and markdown content describing how to handle a specific
task using the available tools. The LLM lists skills on connect and
pulls them on demand, so every time someone asks about, say, the
monthly sales close, the answer is consistent and uses the right
reports.
Prompt Templates are saved starting points for the user's side of the conversation — Jinja-templated prompts with typed arguments (dropdowns, dates, booleans). Authors publish them from the admin page; users pick one, fill in the arguments, and the rendered prompt is sent to the LLM. Use them for frequently-asked analyses like "Sales Analysis", "Manufacturing Analysis", or your own industry-specific workflows.
Both live in Frappe, so they're version-controlled with your site,
shareable across users, and can be shipped by external Frappe apps
through the assistant_skills hook.
FAC ships 22 tools across four plugins: Core (Frappe operations), Data Science (Python execution, analytics, file extraction), Visualization (dashboards and charts), and Custom Tools (the registry for tools contributed by external apps).
Full specification for each tool is in the Tool Reference.
FAC reads your schema from Frappe's metadata API at the moment a tool is called. It keeps no schema copy of its own — no snapshot table, no embedded or vector index of your data model, and no sync command. There is nothing to re-run and no staleness window to reason about.
In practice that means:
get_doctype_info returns custom fields merged inline
with standard fields, along with child-table field definitions, Link
targets, and the DocType's permission rules.FAC does cache a few operational things — whether the server is enabled, the MCP and OAuth endpoint URLs, and dashboard/health statistics. None of them describe your schema or your data.
If you reach FAC through another product that embeds or orchestrates it, that layer may maintain its own schema cache with its own refresh behaviour. Staleness seen through a wrapper is worth tracing there first; FAC itself has no such step.
If you have a Frappe app and want the LLM to reach into it, use the
assistant_tools hook in your app's hooks.py. This is the recommended
path — tools travel with the app, survive upgrades, and stay scoped to
your data model. The same pattern works for Skills via the
assistant_skills hook.
If you need to modify core FAC behaviour instead, write an internal plugin.
See the External App Development guide for the hook contract, and the Plugin Development guide for internal plugins.
FAC uses OAuth 2.0 with PKCE for LLM connections — the LLM never sees
the user's Frappe password. Every tool call is scoped to the calling
user's Frappe and ERPNext roles and permissions: if the user cannot
read a DocType in the desk, they cannot read it through the LLM either.
Every call is logged to Assistant Audit Log with caller, tool,
arguments, and result status, so admins always have a full record of
what the LLM did.
For setup and advanced configuration:
📚 Full docs are at docs.assistantcore.cloud
Common entry points:
For contributors editing this repo, see docs/development/ and Contributing.md.
Frappe Assistant Core is built and maintained in the open. If it saves your team time, please consider sponsoring ongoing maintenance and new features on GitHub Sponsors — recurring or one-time contributions.
Professional implementation, customization, training, and enterprise support are delivered by our official services partner Promantia. Reach them at [email protected], or register your project at https://erp.promantia.in/fac-registration/new. Full details in COMMERCIAL.md.
The software itself remains completely free and open source under AGPL-3.0. Professional services are optional.
AGPL-3.0 — see LICENSE.
For dual-licensing, new partnerships, or sponsorship inquiries, contact [email protected].
Contributions welcome. See Contributing.md for the pull-request workflow and coding standards.
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
ツール
ツール一覧はまだありません。リモートサーバーは、最初のヘルスチェック後に取得されます。
よくある質問
このページで Cursor、Claude Desktop、Claude Code、VS Code 用の stdio 設定をコピーできます。PlugMCP のプロキシではなく、公開元のインストール方法を使います。
このレコードに必須の環境変数は記載されていません。
Frappe Assistant Core は stdio 経由でローカル実行されます。
最終チェックは 2026-11-11 です。 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