AI agents call search to retrieve information from Things without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'search' strongly suggests a query or retrieval operation typical of Read category operations. However, confidence is only moderate (0.6) because the description is empty and provides no explicit confirmation of behavior. Search operations generally have no side effects and low blast radius if misused.
From the tool's definition Tool named 'search' with empty description on a Things productivity app integration server. Based on naming convention and context (sibling tools include add-todo, update, add-project), search would typically retrieve or query todos/projects without side…
Documented attack patterns abuse exactly the kind of access search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Things, and nothing reaches the server without passing your rules. This is the rule we recommend for search:
{
"version": "1",
"default": "deny",
"tools": {
"search": {}
}
}search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
search. It is categorised as a Read tool in the Things MCP Server, which means it retrieves data without modifying state.
Register the Things MCP server in PolicyLayer and add a rule for search: 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 Things. Nothing to install.
search 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 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. 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 is provided by the Things MCP server (jimfilippou/things-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Things, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Things tools catalogued and risk-classified — across an index of 43,000+ MCP servers.