AI agents call search to retrieve information from SupaThings MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the server's primary purpose of reading Things 3 data via SQLite queries and the pattern of similar retrieval-oriented sibling tools, 'search' most likely queries or filters tasks/projects without modifying data. No evidence suggests mutation, deletion, code execution, or financial operations.
From the tool's definition Tool named 'search' on a Things 3 data management server. The server description emphasizes 'read and manage Things 3 data' and includes sibling tools like 'get-anytime', 'get-areas', 'get-headings', 'get-inbox' which are clearly retrieval operations.
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 SupaThings MCP, 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 SupaThings MCP MCP Server, which means it retrieves data without modifying state.
Register the SupaThings 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 SupaThings MCP. 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 SupaThings MCP server (soycanopa/supathings-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SupaThings MCP, 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.
37 SupaThings MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.