Say hello
AI agents call hello to retrieve information from Google Tag Manager MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a simple greeting utility that produces output without accessing, modifying, or executing any operations on external systems. While it doesn't strictly retrieve data, greeting functions are conventionally classified as Read (benign, no-side-effect operations) when they must fit a category. The minimal information returned poses negligible security risk.
From the tool's definition Tool name 'hello' with description 'Say hello' indicates a greeting function with no data retrieval, modification, or side effects.
Attacks that exploit this kind of access
Say hello. It is categorised as a Read tool in the Google Tag Manager MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Tag Manager MCP Server MCP server in PolicyLayer and add a rule for hello: 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 Google Tag Manager MCP Server. Nothing to install.
hello 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 hello 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 hello. 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.
hello is provided by the Google Tag Manager MCP Server MCP server (neep305/mcp-for-gtm). 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 →