get_gdp
AI agents call get_gdp to retrieve information from WorldBank GDP & Employment MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the WorldBank API to fetch GDP statistics. It retrieves existing data without creating, modifying, deleting, executing code, or creating financial obligations. The empty description is a minor gap in specificity, but the server's stated purpose and sibling tools (all read-only: weather data, inflation data, CSV summarization) confirm a Read classification.
From the tool's definition Tool name 'get_gdp' combined with server description stating it 'retrieve[s] economic and labor market data such as GDP and employment indicators' indicates a data retrieval operation with no side effects.
Attacks that exploit this kind of access
get_gdp. It is categorised as a Read tool in the WorldBank GDP & Employment MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WorldBank GDP & Employment MCP Server MCP server in PolicyLayer and add a rule for get_gdp: 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 WorldBank GDP & Employment MCP Server. Nothing to install.
get_gdp 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_gdp 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_gdp. 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_gdp is provided by the WorldBank GDP & Employment MCP Server MCP server (moderator11/mcpserver-gdp). 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 →