Run the market breadth analyzer — measures market participation
AI agents call analyze_breadth 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 and analyzes market metrics (breadth/participation data) from presumably existing data sources. It performs calculations and queries but does not modify state, execute arbitrary code, delete data, or move financial assets. The read-only nature of market analysis tools is further supported by the sibling tools' pattern (fetch_*, analyze_*), which are all data retrieval and analysis operations.
From the tool's definition Tool name 'analyze_breadth' and description 'measures market participation' indicate data analysis/retrieval.
Attacks that exploit this kind of access
Run the market breadth analyzer — measures market participation. 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 analyze_breadth: 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.
analyze_breadth 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 analyze_breadth 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 analyze_breadth. 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.
analyze_breadth 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 →