Full-text search across prompt titles and content
AI agents call search_prompts to retrieve information from Prompteka MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_prompts performs full-text search, which is a read-only query operation that retrieves matching prompts without modifying, executing, or deleting anything. The low severity reflects minimal blast radius — even if an AI agent abuses this tool, it can only discover existing prompts in the local library, not alter or destroy data.
From the tool's definition Tool description states 'Full-text search across prompt titles and content' — a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Full-text search across prompt titles and content. It is categorised as a Read tool in the Prompteka MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Prompteka MCP Server MCP server in PolicyLayer and add a rule for search_prompts: 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 Prompteka MCP Server. Nothing to install.
search_prompts 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 search_prompts 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 search_prompts. 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.
search_prompts is provided by the Prompteka MCP Server MCP server (webdevguyrg/prompteka-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 →