AI agents call xbrl_edgar_search 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 'search' suffix and integration with SEC EDGAR—a public financial database—indicates this tool queries and retrieves filing data without modifying, deleting, or executing arbitrary operations. While the empty description limits confidence slightly, the context of read-only tools (browse_taxonomy, company_facts, concept_details) on the same server and the 'search' operation pattern support classification as Read.
From the tool's definition Tool name contains 'search' and operates within an EDGAR (SEC filing database) context. The server description indicates this tool is part of 'SEC EDGAR integration' for processing and analyzing filings.
Attacks that exploit this kind of access
xbrl_edgar_search. 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_edgar_search: 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_edgar_search 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_edgar_search 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_edgar_search. 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_edgar_search 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 →