AI agents call get_market_benchmarks to retrieve information from Wrds without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves market benchmark data for financial analysis, which is a read-only query operation with no side effects. Severity is medium because financial benchmark data could inform investment decisions, but the tool itself performs no writes, deletes, or financial transactions. The empty description and reliance on naming convention and context reduce confidence slightly from high to medium-high.
From the tool's definition Tool name 'get_market_benchmarks' indicates retrieval of benchmark data; sibling tools on this server (get_bond_price_history, get_bond_yield_history, get_coverage_ratios, etc.) are all Read operations that query financial datasets without modification.
Attacks that exploit this kind of access
get_market_benchmarks. It is categorised as a Read tool in the Wrds MCP Server, which means it retrieves data without modifying state.
Register the Wrds MCP server in PolicyLayer and add a rule for get_market_benchmarks: 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 Wrds. Nothing to install.
get_market_benchmarks 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_market_benchmarks 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_market_benchmarks. 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_market_benchmarks is provided by the Wrds MCP server (marianosalinas/wrds_mcp). 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 →