red-mcp-server

# Red MCP Server

Red is an open-source [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that connects AI assistants and MCP clients to [Big Red Cloud](https://www.bigredcloud.com) accounting data through a set of controlled MCP tools.

Supported customer platforms today are **ChatGPT**, **Claude**, and **Mistral** (including [Vibe](https://chat.mistral.ai/chat)). Other MCP clients may work technically, but they are not treated as officially supported platforms. Red uses platform detection only for anonymous operational telemetry (see [Privacy-safe telemetry](#privacy-safe-telemetry)).

Instead of calling the Big Red Cloud REST API directly, users work in plain language. The server translates requests into structured API calls and applies safety checks around anything that changes data.

With Red, a connected user can:

- **Review** Big Red Cloud data with read-only lookups (customers, suppliers, products, invoices, quotes, nominal reports, and more).
- **Review before posting** — see a plain-English preview of new records before anything is written to Big Red Cloud.
- **Create, update, or delete** records only after explicit confirmation.
- **Ask Big Red Cloud how-to and training questions** — Red answers using official support articles, customer documentation, screenshots, and webinar resources. These help tools do not require a connected company.

---

## Why open source?

We believe AI infrastructure should be transparent. Customers should be able to inspect the software that connects their accounting data to AI assistants.

Our competitive advantage is not the connector itself; it is our accounting platform, our expert bookkeeping advice, our customer experience, and the value we build on top of it.

By open-sourcing Red, we hope to encourage trust, community contributions, and wider adoption of open standards.

---

## Features

- Secure company connection flow (one-time connection page; no credentials in chat)
- Pre-confirm validation of company connection credentials on the connection page (single-company form or multi-company CSV upload)
- Partial connection results — invalid keys are rejected before confirm and reported in `failedCompanies`
- Hosted HTTP `connectionRef` / `activeConnectionRef` so MCP clients can silently reuse a confirmed connection across supported session changes; kept in tool JSON, not shown to end users
- Privacy-safe anonymous operational telemetry (platform, environment, tool name, connected-company count) — see [docs/TELEMETRY.md](docs/TELEMETRY.md)
- Company readiness check (`brc_company_readiness_check`) for connected companies
- Read-only Big Red Cloud lookups
- Customer, supplier, product, sales rep, VAT, and analysis category tools
- Sales quotes, invoices, credit notes, purchases, payments, and cash tools
- Preview-before-posting confirmation flow for create, update, delete, batch, and email actions
- VAT and transaction safety checks
- Sales invoice safeguards, including multi-line generated-reference validation, Gross Price Entry `priceBasis` handling, Sales VAT category validation, placeholder product ID blocking, and CR analysis category confirmation
- Session audit log of writes made through the MCP session
- Official Big Red Cloud help answers from Freshdesk articles, customer documentation, screenshots, and webinars — no company connection required
- Local stdio and hosted HTTP transports

---

## Security and safety model

Red is designed so that AI-driven access to accounting data stays controlled and auditable.

- **No credentials in the repository.** Company connection credentials and secrets are never committed. Configuration is supplied at runtime through environment variables.
- **No credentials in chat.** Company connection credentials must not be pasted into chat. Companies are connected through the secure Red connection page, where credentials are entered directly — not in the chat window.
- **Session-scoped connections.** A connected company stays available for about the configured session duration and is held in session memory (or an optional shared connection store in hosted deployments). Where supported, connection handling is resilient across MCP session rotation so clients can reuse `connectionRef` / `activeConnectionRef` without asking the user to reconnect.
- **Pre-confirm validation.** Company connection credentials submitted on the connection page are validated against Big Red Cloud before they are stored. Invalid or expired credentials are not saved; they appear in `failedCompanies` at confirmation time.
- **Credential invalidation.** Only confirmed authentication failures clear a stored company credential. Endpoint, validation, permission, timeout, and server failures are not treated as an expired API key.
- **User-facing presentation.** `connectionRef`, session IDs, and other MCP diagnostics are for tool arguments only. Assistants must not show `redconn_…` values or internal connection metadata to normal users unless dev mode is enabled or the user explicitly asks for technical details.
- **Configurable session duration.** How long connections last is controlled by `BRC_API_KEY_TTL_MINUTES`. User-facing wording (connection page, getting-started text, connection status) is derived from that value — not hardcoded.
- **Explicit confirmation for writes.** Create, update, delete, batch, and email actions require an explicit confirmation flag after a preview before posting has been shown.
- **Preview before posting.** The first call to a write tool returns a payload preview rather than performing the action. Nothing is written to Big Red Cloud until you confirm.
- **Read and write are separated.** Read-only lookups are clearly distinct from actions that change data.
- **Audit log.** Writes made through the MCP session are recorded in a session audit log; read-only calls are not logged.
- **Deployment flags.** Update, delete, email, batch, and operator/dev tools can each be disabled per deployment, in which case the matching tools return a permission message instead of calling Big Red Cloud.

### Sales invoice safety checks

Sales invoice handling includes:

- **Gross Price Entry** requires an explicit `priceBasis` of `gross` or `net` so VAT is never guessed.
- **Sales VAT rates only.** Sales invoices must use a Sales VAT category; purchase VAT rates are blocked, even when the percentage matches.
- **Placeholder product IDs** (`productId` `0` and `1`) are treated as placeholders and blocked before preview-before-posting and post.
- **Multi-line generated-reference invoices** (`brc_create_sales_invoice_gen_ref`) require each `productTrans` line to include its own `acEntries` analysis allocation. Line net/VAT/gross reconciliation, analysis allocation totals, header totals, and required product/VAT/analysis fields are validated before posting; failures return structured field-level errors.
- **`note`** defaults to the customer name unless a note is explicitly provided, and is never set to a product name.
- **`deliveryTo`** is included only when a delivery address is explicitly provided.
- **Plain-language results.** Technical HTTP status codes are translated into plain-language messages for users.

---

## Architecture

Two entry points share one tool registry:

| Entry | File | Transport | Use case |
| ----- | ---- | --------- | -------- |
| Local stdio | `src/index.ts` | `StdioServerTransport` | An MCP client spawns `node build/index.js` |
| Hosted HTTP | `src/remote.ts` | Streamable HTTP on `/mcp` | `npm run start` — one MCP server per session |

Key shared modules:

- `src/server.ts` — MCP server factory and stdio singleton
- `src/register_all_tools.ts` — central tool registration; wraps the server so disabled skills register a permission-message blocker instead of the real tool, and so write tools get preview-before-posting/confirmation handling
- `src/config/server_config.ts` — deployment skill gating driven by the `BRC_ALLOW_*` flags
- `src/config/mcp_config.ts` — MCP server instructions, connection-safety rules, and connectionRef presentation rules
- `src/shared.ts` — Big Red Cloud HTTP client, session-scoped connections, audit log, and helpers
- `src/read_connection_metadata.ts` — connection status metadata echoed on tool responses (including `activeConnectionRef` for hosted clients)
- `src/auth/connection_presentation.ts` — user-facing TTL wording and assistant presentation hints
- `src/auth/credential_validation.ts` — BRC read validation before storing company connection credentials
- `src/guards/` — transaction, reference, VAT category, product line, and write-confirmation safety checks
- `src/auth/` — secure connection flow, connection store (memory or Cosmos), connection page, and credential persistence
<<<<<<< HEAD
- `src/telemetry/` — anonymous client/session identity and platform detection for hosted operational telemetry
=======
>>>>>>> company-github/main
- `src/brc-edu/` — Freshdesk articles, customer documentation, webinar indexes, screenshots, and unified help search
- `src/edu/` — shared help-resource loading, enrichment, workbook parsing, and storage configuration
- `src/tools/edu/` — read-only help tools: `brc_find_help_resources` and `brc_get_help_resource_details`

Domain logic lives under `src/tools/`, with generic create/update/delete/list/batch helpers in `src/tools/general/`.

### Technology

- TypeScript / Node.js (ES modules)
- `@modelcontextprotocol/sdk`
- Zod for tool input validation
- Express + Streamable HTTP for hosted mode

---

## Requirements

- Use a current LTS version of Node.js.
- npm (bundled with Node.js).

---

## Installation

```bash
npm install
npm run build
```

If a `.env.example` file is provided, copy it to `.env` and adjust the values:

```bash
cp .env.example .env
```

Never commit your `.env` file or any real credentials.

---

## Running

Hosted HTTP server:

```bash
npm run start
# Serves the MCP endpoint at http://localhost:3000/mcp
```

Local stdio server:

```bash
n