brc_red_help
MANDATORY FOR RED-HELP COMMANDS: When the user's message starts with red-help or /red-help, call this tool before searching for or calling any accounting action tool. Red Help — Manual Instructions and Resources. This tool gives manual Big Red Cloud instructions and searches Freshdesk, YouTube, B...
This record as markdown: /tools/io-github-bigredcloud-red-mcp-server/brc-red-help.md
What brc_red_help does on Red by Big Red Cloud
AI agents call brc_red_help 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Text after the red-help command, for example how do I add a sales invoice or add a customer manually. |
Parameters from the server's own tool schema.
Why brc_red_help is rated Critical
An AI agent that decides to call brc_red_help 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.
Attacks that exploit this kind of access
The rule that runs brc_red_help safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Red by Big Red Cloud, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For brc_red_help, this is the rule to start with:
brc_red_help is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Red by Big Red Cloud, apply this rule, and every brc_red_help call is checked against it from then on.
Questions about brc_red_help
MANDATORY FOR RED-HELP COMMANDS: When the user's message starts with red-help or /red-help, call this tool before searching for or calling any accounting action tool. Red Help — Manual Instructions and Resources. This tool gives manual Big Red Cloud instructions and searches Freshdesk, YouTube, BRC Edu, webinars, screenshots and other available help resources. red-help means the user does not want Red to perform the accounting action — never replace a red-help request with create, update, delete or post tools. Pass the text after red-help as the query. Examples: User: "red-help how do I add a sales invoice" Call: brc_red_help({ query: "how do I add a sales invoice" }) User: "/red-help add a customer manually" Call: brc_red_help({ query: "add a customer manually" }) Searchable for common accounting-help topics: manual instructions, how to, help article, tutorial, screenshots, sales invoice, purchase invoice, customer, supplier, bank reconciliation, credit note, payment, receipt, VAT, reports and company setup. Read-only. Does not require a connected company, companyName, connectionRef, or accounting record details. After results, call brc_get_help_resource_details for the best Freshdesk match with includeImages=true and imagePresentation=links. Recommended entry point for reserved red-help / /red-help commands. brc_find_help_resources remains available for backward compatibility. It is categorised as a Destructive tool in the Red by Big Red Cloud MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
brc_red_help accepts 1 parameter: query. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Red by Big Red Cloud MCP server in PolicyLayer and add a rule for brc_red_help: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Red by Big Red Cloud. Nothing to install.
brc_red_help is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the brc_red_help rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for brc_red_help. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
brc_red_help is provided by the Red by Big Red Cloud MCP server (https://red.bigredcloud.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Red by Big Red Cloud, and thousands of servers like it.
Across the catalogue