get_watchlist
AI agents call get_watchlist to retrieve information from MCP YFinance Stock Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves a user's watchlist—stored preferences of stocks to monitor. This is a pure Read operation with no side effects, reversible changes, code execution, or financial transactions. The empty description is compensated by the clear naming convention and server context.
From the tool's definition Tool name 'get_watchlist' and server context indicates data retrieval. Server description emphasizes 'retrieve real-time stock data' and 'manage watchlists.' Sibling tools like 'add_to_watchlist' (Write) and read-only analysis tools confirm this is a…
Attacks that exploit this kind of access
get_watchlist. It is categorised as a Read tool in the MCP YFinance Stock Server MCP Server, which means it retrieves data without modifying state.
Register the MCP YFinance Stock Server MCP server in PolicyLayer and add a rule for get_watchlist: 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 MCP YFinance Stock Server. Nothing to install.
get_watchlist 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 get_watchlist 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 get_watchlist. 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.
get_watchlist is provided by the MCP YFinance Stock Server MCP server (sauniket/mcp-yfinance-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 →