Fetch current market snapshot — equities, commodities, FX, rates,
AI agents call fetch_market_data to retrieve information from Market Brief without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves current market information (prices, rates, etc.) for display and analysis. It is a read-only operation with no side effects, no data modification, no code execution, and no financial transactions. The low severity reflects that misuse would only expose market data that is typically public.
From the tool's definition Tool name is "fetch_market_data" and description states "Fetch current market snapshot — equities, commodities, FX, rates".
Attacks that exploit this kind of access
Fetch current market snapshot — equities, commodities, FX, rates,. It is categorised as a Read tool in the Market Brief MCP Server, which means it retrieves data without modifying state.
Register the Market Brief MCP server in PolicyLayer and add a rule for fetch_market_data: 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 Market Brief. Nothing to install.
fetch_market_data 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 fetch_market_data 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 fetch_market_data. 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.
fetch_market_data is provided by the Market Brief MCP server (yukipanpan/marketbrief). 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 →