AI agents call get-headings 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.
The tool name 'get-' indicates a retrieval action with no side effects. While the description is empty, the naming pattern and context of sibling read-only tools (all starting with 'get-') strongly suggest this retrieves structural data from the Things 3 database. No creation, modification, deletion, or execution of external commands is implied. This is a low-severity Read operation as it only queries existing data.
From the tool's definition Tool name 'get-headings' paired with sibling tools like 'get-areas', 'get-inbox', 'get-project-structure', and 'get-logbook' which are all retrieval operations. The tool appears designed to query/retrieve heading data from Things 3.
Documented attack patterns abuse exactly the kind of access get-headings 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 get-headings:
{
"version": "1",
"default": "deny",
"tools": {
"get-headings": {}
}
}get-headings 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.
get-headings. 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 get-headings: 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.
get-headings 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-headings 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-headings. 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-headings 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.