AI agents call xbrl_load_filing 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.
Loading a filing retrieves and parses financial document data without modifying it. This is a Read operation. Severity is medium (not low) because XBRL financial filings contain sensitive corporate financial information; unauthorized or careless access could expose confidential earnings, strategic data, or material non-public information.
From the tool's definition Tool name is 'xbrl_load_filing' which follows the semantic pattern of other Read tools on this server (xbrl_browse_taxonomy, xbrl_concept_details, xbrl_company_facts, xbrl_compare_filings).
Attacks that exploit this kind of access
xbrl_load_filing. 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_load_filing: 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_load_filing 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_load_filing 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_load_filing. 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_load_filing 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 →