Find prompts in PromptingBox that are semantically relevant to the given context. Uses AI-powered semantic search — matches by meaning, not just keywords. Great for discovering prompts related to what the user is currently working on.
AI agents call find_relevant to retrieve information from PromptingBox MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (prompts) based on semantic relevance matching. It is a read-only query operation analogous to a search or filter function. No data is created, modified, deleted, or executed as a result of calling this tool. The blast radius of misuse is minimal — an agent might retrieve unintended prompts, but cannot cause data loss, financial harm, or system-level damage.
From the tool's definition Tool performs semantic search to 'find prompts' and 'discover prompts' — a retrieval operation with no side effects. The description emphasizes searching and matching by meaning, with no mention of modifying, deleting, or executing any operations.
Attacks that exploit this kind of access
Find prompts in PromptingBox that are semantically relevant to the given context. Uses AI-powered semantic search — matches by meaning, not just keywords. Great for discovering prompts related to what the user is currently working on. It is categorised as a Read tool in the PromptingBox MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PromptingBox MCP Server MCP server in PolicyLayer and add a rule for find_relevant: 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 PromptingBox MCP Server. Nothing to install.
find_relevant 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 find_relevant 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 find_relevant. 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.
find_relevant is provided by the PromptingBox MCP Server MCP server (promptingbox/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
find_relevant is one line of PromptingBox MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →