AI agents call xbrl_smart_summary 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 to generate summaries from XBRL filings based on its name and position among other read/analysis tools like xbrl_browse_taxonomy, xbrl_concept_details, and xbrl_company_facts. Summarization is a retrieval operation with no side effects. Confidence is moderate due to missing description, but the naming convention and peer tools in the analytical cluster support a Read classification.
From the tool's definition Tool name 'xbrl_smart_summary' combined with XBRL filing analysis context suggests data retrieval and summarization. No description provided to confirm, but 'summary' indicates a read-only analytical operation rather than creation, modification, or deletion.
Attacks that exploit this kind of access
xbrl_smart_summary. 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_smart_summary: 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_smart_summary 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_smart_summary 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_smart_summary. 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_smart_summary 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 →