Get the full text of a RouterOS documentation page by ID or title. Use after routeros_search identifies a relevant page. Pass the numeric page ID (from search results) or the exact page title (case-insensitive). Returns: plain text, code blocks, and callout blocks (notes, warnings, info, tips). C...
AI agents call routeros_get_page to retrieve information from Rosetta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs document retrieval without side effects. It searches and fetches RouterOS documentation content from SQLite FTS5 storage. The description shows no write, delete, or execute operations—only returning existing documentation text. Even the large page handling behavior is non-destructive, simply returning a table of contents instead of truncated text.
From the tool's definition Tool retrieves documentation pages from RouterOS by ID or title and returns 'plain text, code blocks, and callout blocks.' No modification, deletion, or execution capabilities described.
Documented attack patterns abuse exactly the kind of access routeros_get_page gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rosetta, and nothing reaches the server without passing your rules. This is the rule we recommend for routeros_get_page:
{
"version": "1",
"default": "deny",
"tools": {
"routeros_get_page": {}
}
}routeros_get_page is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the full text of a RouterOS documentation page by ID or title. Use after routeros_search identifies a relevant page. Pass the numeric page ID (from search results) or the exact page title (case-insensitive). Returns: plain text, code blocks, and callout blocks (notes, warnings, info, tips). Callouts contain crucial caveats and edge-case details — always review them. Large page handling: max_length defaults to 16000. When page content exceeds it, pages with sections return a table of contents instead of truncated text. The TOC response surfaces high-signal content up front so you rarely need a second call: top properties (name + type + description), related_videos (FTS match on page title), callout_summary (count by type), and the section list (heading, level, char_count, deep-link URL). Re-call with the section parameter for full section text. Section parameter: Pass a section heading or anchor_id (from the TOC) to get that section. It is categorised as a Read tool in the Rosetta MCP Server, which means it retrieves data without modifying state.
Register the Rosetta MCP server in PolicyLayer and add a rule for routeros_get_page: 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 Rosetta. Nothing to install.
routeros_get_page is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the routeros_get_page 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 routeros_get_page. 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.
routeros_get_page is provided by the Rosetta MCP server (tikoci/rosetta). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rosetta, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Rosetta tools catalogued and risk-classified — across an index of 43,000+ MCP servers.