search_tasks
AI agents call search_tasks to retrieve information from Things Cloud MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations are fundamentally retrieval tools that query and return data without modifying state. Although the description is empty, the tool name and server context strongly indicate read-only behavior. No side effects are entailed by searching tasks. Severity is low because reading task data poses minimal risk even if misused by an AI agent.
From the tool's definition Tool is named 'search_tasks' and is part of a Things3 task management API. Sibling tools on the server show operations like 'add_checklist_item', 'assign_tags', 'complete_task', and 'delete_project', establishing that this server manages tasks.
Attacks that exploit this kind of access
search_tasks. It is categorised as a Read tool in the Things Cloud MCP MCP Server, which means it retrieves data without modifying state.
Register the Things Cloud MCP server in PolicyLayer and add a rule for search_tasks: 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 Cloud MCP. Nothing to install.
search_tasks 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_tasks 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_tasks. 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_tasks is provided by the Things Cloud MCP server (nkootstra/things). 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 →