AI agents call list_saved_reports to retrieve information from StocksMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read operation that queries and retrieves metadata about saved reports from local storage. It has no capacity to modify, delete, execute code, or affect financial transactions. The blast radius of misuse is minimal - an agent could only access information already stored locally. Confidence is high due to clear evidence in both the tool name and description indicating a retrieval operation.
From the tool's definition Tool name contains 'list' and description states 'Lists metadata summary for all stock analysis reports saved in local storage' - retrieves and queries data with no modification or side effects.
Attacks that exploit this kind of access
Lists metadata summary for all stock analysis reports saved in local storage. It is categorised as a Read tool in the StocksMCP MCP Server, which means it retrieves data without modifying state.
Register the Stocks MCP server in PolicyLayer and add a rule for list_saved_reports: 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 StocksMCP. Nothing to install.
list_saved_reports 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 list_saved_reports 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 list_saved_reports. 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.
list_saved_reports is provided by the Stocks MCP server (pawanthanay/stocksmcp). 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 →