AI agents call xbrl_concept_details 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 suggests querying details about XBRL concepts (concepts are definitional elements in financial taxonomies). No description provided, but taxonomy browsing and concept inspection are inherently read-only operations with no side effects. Confidence reduced slightly due to empty description, but naming convention and server context strongly indicate information retrieval.
From the tool's definition Tool name 'xbrl_concept_details' and server context indicate retrieval of XBRL concept metadata from taxonomy. The 'concept_details' pattern (get/fetch details) aligns with Read operations.
Attacks that exploit this kind of access
xbrl_concept_details. 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_concept_details: 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_concept_details 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_concept_details 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_concept_details. 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_concept_details 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 →