Search for to-dos by title or notes content. Uses AppleScript/JXA (macOS only).
AI agents call search-todos to retrieve information from Things App MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches existing tasks based on search criteria. It has no side effects, does not modify, delete, or execute operations. The blast radius of misuse is minimal—an agent can only discover information about existing todos, which is a read-only operation.
From the tool's definition Tool name 'search-todos' and description 'Search for to-dos by title or notes content' indicate querying/retrieval with no modification of data. Uses AppleScript/JXA for querying, not for write, execute, or destructive operations.
Attacks that exploit this kind of access
Search for to-dos by title or notes content. Uses AppleScript/JXA (macOS only). It is categorised as a Read tool in the Things App MCP MCP Server, which means it retrieves data without modifying state.
Register the Things App MCP server in PolicyLayer and add a rule for search-todos: 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 App MCP. Nothing to install.
search-todos 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-todos 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-todos. 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-todos is provided by the Things App MCP server (lucas-flatwhite/things-app-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 →