\uC0AC\uC6A9\uC790\uC5D0\uAC8C \uC774\uB984\uACFC \uC5B8\uC5B4\uB97C \uC785\uB825\uBC1B\uC544 \uD574\uB2F9 \uC5B8\uC5B4\uB85C \uC778\uC0AC\uB9D0\uC744 \uBC18\uD658\uD569\uB2C8\uB2E4.
AI agents call greeting to retrieve information from TypeScript MCP Server Boilerplate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The greeting tool performs a simple read-only operation: it accepts user input (name and language) and returns a computed greeting string. There is no data persistence, no external API calls with side effects, no code execution on the host system, and no destructive or financial operations. This clearly falls under the Read category as it retrieves/generates data without side effects.
From the tool's definition Tool name 'greeting' and description indicate it receives a user's name and language as input and returns a greeting message in the specified language. This is a pure query/retrieval operation with no side effects, data modification, or external state changes.
Attacks that exploit this kind of access
\uC0AC\uC6A9\uC790\uC5D0\uAC8C \uC774\uB984\uACFC \uC5B8\uC5B4\uB97C \uC785\uB825\uBC1B\uC544 \uD574\uB2F9 \uC5B8\uC5B4\uB85C \uC778\uC0AC\uB9D0\uC744 \uBC18\uD658\uD569\uB2C8\uB2E4. It is categorised as a Read tool in the TypeScript MCP Server Boilerplate MCP Server, which means it retrieves data without modifying state.
Register the TypeScript MCP Server Boilerplate MCP server in PolicyLayer and add a rule for greeting: 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 TypeScript MCP Server Boilerplate. Nothing to install.
greeting 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 greeting 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 greeting. 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.
greeting is provided by the TypeScript MCP Server Boilerplate MCP server (you0best/my-mcp-server). 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 →