AI agents use xbrl_export_json to create or update resources in Arelle — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arelle environment.
Export tools generate new data outputs (JSON serialization of XBRL content) which constitutes a Write operation. While the description is empty, the naming pattern and server context (financial filing analysis) suggest this extracts and formats XBRL data into JSON format—a reversible data transformation/creation.
From the tool's definition Tool name 'xbrl_export_json' indicates data export/serialization functionality. In the context of XBRL filing operations (per server description), export typically creates or writes output files/data without irreversibly deleting originals.
Attacks that exploit this kind of access
xbrl_export_json. It is categorised as a Write tool in the Arelle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arelle MCP server in PolicyLayer and add a rule for xbrl_export_json: 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_export_json is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the xbrl_export_json 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_export_json. 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_export_json 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 →