search_disclosures
AI agents call search_disclosures to retrieve information from Dart Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries corporate disclosure data from Korea's DART system. It has no side effects—it does not create, modify, delete, or execute operations. The lack of a description is not concerning given the clear semantic meaning of 'search_disclosures' and the homogeneous Read-category functions in the sibling tool set.
From the tool's definition Tool name 'search_disclosures' combined with server description indicating it 'enables searching corporate disclosures' and contextual sibling tools (get_company_info, get_financial_indicators, get_financial_statements, etc.) all performing retrieval…
Attacks that exploit this kind of access
search_disclosures. It is categorised as a Read tool in the Dart Search MCP Server, which means it retrieves data without modifying state.
Register the Dart Search MCP server in PolicyLayer and add a rule for search_disclosures: 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 Dart Search. Nothing to install.
search_disclosures 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 search_disclosures 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 search_disclosures. 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.
search_disclosures is provided by the Dart Search MCP server (memorise8/dart-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 →