AI agents call xbrl_dts_comparison 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.
DTS comparison is a data analysis and retrieval operation that queries and compares taxonomy or schema structures. It does not create, modify, delete, or execute arbitrary code. The medium severity reflects that while it only reads data, XBRL filings contain sensitive financial information, and comparative analysis could inform decisions affecting stakeholders.
From the tool's definition Tool name 'xbrl_dts_comparison' indicates comparison of DTS (Document Type System) schemas or structures within XBRL filings.
Attacks that exploit this kind of access
xbrl_dts_comparison. 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_dts_comparison: 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_dts_comparison 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_dts_comparison 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_dts_comparison. 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_dts_comparison 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 →