AI agents call get_data_catalog 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.
The tool name and server context indicate this retrieves or lists available data sources/metadata rather than executing queries or modifying data. Despite the empty description, the naming convention aligns with read-only data catalog discovery. Severity is low as catalog retrieval carries minimal blast radius—it exposes what data exists but not the data itself.
From the tool's definition Tool name 'get_data_catalog' indicates retrieval of catalog information. Server context shows this is part of WRDS financial data access tools that query data without modification. Sibling tools are all 'get_*' retrieval operations.
Attacks that exploit this kind of access
get_data_catalog. 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_data_catalog: 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_data_catalog 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_data_catalog 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_data_catalog. 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_data_catalog 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 →