get_prompt
AI agents call get_prompt to retrieve information from MCP Test MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'get_prompt' strongly suggests a read-only operation that retrieves prompt information without side effects. Within a testing harness context, this would be used to fetch prompt definitions for validation. The empty description lowers confidence slightly, but the semantic meaning of 'get' universally indicates data retrieval rather than modification or execution.
From the tool's definition Tool name 'get_prompt' with no description provided. Based on naming convention and context within a testing harness, this appears to be a retrieval operation for prompt data.
Attacks that exploit this kind of access
get_prompt. It is categorised as a Read tool in the MCP Test MCP MCP Server, which means it retrieves data without modifying state.
Register the MCP Test MCP server in PolicyLayer and add a rule for get_prompt: 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 MCP Test MCP. Nothing to install.
get_prompt 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_prompt 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_prompt. 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_prompt is provided by the MCP Test MCP server (rdwj/mcp-test-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 →