AI agents call get_credit_ratings 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 credit ratings data, which is a read operation with no side effects. Severity is medium rather than low because credit ratings are sensitive financial intelligence that could influence investment decisions if manipulated by a compromised agent, though the tool itself only reads data.
From the tool's definition Tool name 'get_credit_ratings' indicates a retrieval operation. The server description confirms this tool is part of a suite for 'querying' financial data, with sibling tools following read-only patterns (get_bond_*, get_company_*, etc.).
Attacks that exploit this kind of access
get_credit_ratings. 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_credit_ratings: 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_credit_ratings 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_credit_ratings 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_credit_ratings. 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_credit_ratings 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 →