# brc_route_request

MANDATORY FIRST STEP for Red requests that may create, update, delete, post, email, or batch-write company data. Classify and route a user request between Red's two main behaviours: action (perform the accounting workflow) and help (manual Big Red Cloud instructions). Also returns connection, read, unsupported_action, or unknown when those specialised modes apply. Pass the user's complete original message — never only a confirmation word such as yes or delete it when starting a new action. Action mode always returns a non-empty preferredTools list, allowedTools, and an opaque short-lived routeToken — pass that routeToken on every subsequent transactional tool call for the permitted workflow, including after lookup and preview. unsupported_action means Red cannot map the request to an enabled workflow — explain that to the user; do not invent a routeToken. Help mode runs the unified help search, returns manual resources, sets blockTransactionalTools true, and never issues a transactional routeToken. How-to wording (how do I, how can I, show me how, tell me how, where do I, what are the steps, manual steps for, red-help, /red-help) → mode help. Explicit action wording (add a customer, create a sales invoice, delete customer ABC, can you add a customer for me) → mode action with routeToken. A routeToken does not replace preview-before-posting or user confirmation (confirmWrite). Help mode does not persist — each brc_route_request call is classified independently unless returning confirmation continuation for a pending preview. Read-only classification and help search. Does not require a connected company. When a company is already connected, pass connectionRef silently so the routeToken can bind to that connection and survive MCP session rotation.

Agent View of the PolicyLayer registry record for `brc_route_request`. HTML page: https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-route-request

## Facts

- Tool: `brc_route_request`
- Server: Red by Big Red Cloud (`https://red.bigredcloud.com/mcp`) — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server.md
- Homepage: https://github.com/BigRedCloud/red-mcp-server
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `message` | string | yes | The user's complete original message to classify, for example add a customer or how do I add a customer. |
| `connectionRef` | string | no | Opaque Red connection reference returned by brc_confirm_company_connection. Pass this exact value on every later tool call when the MCP client rotates session i |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "brc_route_request",
    "arguments": {
      "message": "<message>"
    }
  }
}
```

## Why brc_route_request is rated Critical

An AI agent that decides to call brc_route_request doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Red by Big Red Cloud is gone. There is no undo for destructive operations.

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call brc_route_request to permanently remove resources in Red by Big Red Cloud, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Red by Big Red Cloud:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "brc_route_request"
  ]
}
```

## Other tools on Red by Big Red Cloud (158)

- `brc_clear_all_company_api_keys` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-clear-all-company-api-keys.md
- `brc_clear_audit_log` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-clear-audit-log.md
- `brc_clear_company_api_key` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-clear-company-api-key.md
- `brc_delete_accrual` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-accrual.md
- `brc_delete_allocation_resolver` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-allocation-resolver.md
- `brc_delete_bank_account` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-bank-account.md
- `brc_delete_cash_payment` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-cash-payment.md
- `brc_delete_cash_receipt` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-cash-receipt.md
- `brc_delete_customer` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-customer.md
- `brc_delete_nominal_journal_batch` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-nominal-journal-batch.md
- `brc_delete_payment` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-payment.md
- `brc_delete_prepayment` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-prepayment.md
- `brc_delete_product` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-product.md
- `brc_delete_purchase` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-purchase.md
- `brc_delete_quote` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-quote.md
- `brc_delete_sales_credit_note` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-sales-credit-note.md
- `brc_delete_sales_entry` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-sales-entry.md
- `brc_delete_sales_invoice` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-sales-invoice.md
- `brc_delete_sales_rep` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-sales-rep.md
- `brc_delete_supplier` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-delete-supplier.md
- `brc_red_help` — Destructive — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-red-help.md
- `brc_getting_started` — Execute — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-getting-started.md
- `brc_start_company_connection` — Execute — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-start-company-connection.md
- `brc_create_payment` — Financial — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-create-payment.md
- `brc_batch_cash_payments` — Read — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-batch-cash-payments.md
- `brc_batch_cash_receipts` — Read — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-batch-cash-receipts.md
- `brc_batch_customers` — Read — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-batch-customers.md
- `brc_batch_payments` — Read — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-batch-payments.md
- `brc_batch_products` — Read — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-batch-products.md
- `brc_batch_purchases` — Read — https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server/brc-batch-purchases.md
- …and 128 more: https://policylayer.com/tools/io-github-bigredcloud-red-mcp-server.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-bigredcloud-red-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-bigredcloud-red-mcp-server