AI agents call xbrl_browse_taxonomy to retrieve information from Arelle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests browsing or querying taxonomy metadata without modification or execution. While the description is empty (lowering confidence slightly), the naming pattern and context of sibling analytical tools indicate this is a Read operation for financial data inspection, with low blast radius if misused by an agent.
From the tool's definition Tool name 'xbrl_browse_taxonomy' indicates querying/inspection of taxonomy data. No description provided, but 'browse' and 'taxonomy' suggest read-only data retrieval from XBRL taxonomy structures, similar to sibling tools like 'xbrl_concept_details' and…
Attacks that exploit this kind of access
xbrl_browse_taxonomy. It is categorised as a Read tool in the Arelle MCP Server, which means it retrieves data without modifying state.
Register the Arelle MCP server in PolicyLayer and add a rule for xbrl_browse_taxonomy: 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 Arelle. Nothing to install.
xbrl_browse_taxonomy 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 xbrl_browse_taxonomy 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 xbrl_browse_taxonomy. 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.
xbrl_browse_taxonomy is provided by the Arelle MCP server (thekinghippopotamus/arelle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →