AI agents call xbrl_get_exhibits 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 appears designed to retrieve or fetch exhibit documents from XBRL filings, consistent with Read category operations. No description is provided, which lowers confidence slightly, but the 'get_' prefix strongly suggests a retrieval operation. Exhibits are typically static documents attached to filings, and retrieving them has no side effects on the filing data itself.
From the tool's definition Tool name 'xbrl_get_exhibits' uses the verb 'get', which indicates retrieval of data without modification. Exhibits in XBRL filings are attachments/documents that are read, not created or modified.
Attacks that exploit this kind of access
xbrl_get_exhibits. 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_get_exhibits: 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_get_exhibits 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_get_exhibits 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_get_exhibits. 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_get_exhibits 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 →