証券をキーワードで検索します。会社名、ティッカー等から候補を見つけます。
AI agents call search_securities to retrieve information from Bloomberg MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Bloomberg's security database to find securities matching search criteria. It retrieves information without modifying data, executing commands, or causing side effects. It belongs in the Read category as a straightforward lookup/search operation. Severity is low because misuse would at worst return unwanted market data with no operational impact.
From the tool's definition Tool name 'search_securities' and description indicate a search function that retrieves security candidates by keyword (company name, ticker). The verb 'search' and absence of any language about modification, deletion, or execution confirms read-only behavior.
Attacks that exploit this kind of access
証券をキーワードで検索します。会社名、ティッカー等から候補を見つけます。. It is categorised as a Read tool in the Bloomberg MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bloomberg MCP Server MCP server in PolicyLayer and add a rule for search_securities: 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 Bloomberg MCP Server. Nothing to install.
search_securities 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_securities 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_securities. 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_securities is provided by the Bloomberg MCP Server MCP server (shunsuketamura06/simple-mcp-server). 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 →