search_tasks
AI agents call search_tasks to retrieve information from Amplenote Cache MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries task data from a local SQLite cache without side effects. Despite the empty description, the tool's name and server context (search/retrieval operations) and parallel sibling tools all indicate a read-only operation. No capability to modify, delete, execute code, or commit financial obligations is evident.
From the tool's definition Tool name 'search_tasks' with empty description; sibling tools (list_tasks, query_tasks, get_tasks_by_note) all perform read operations on cached task data.
Attacks that exploit this kind of access
search_tasks. It is categorised as a Read tool in the Amplenote Cache MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amplenote Cache MCP Server 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 Amplenote Cache MCP Server. 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 Amplenote Cache MCP Server MCP server (mikekwright/amplenote-cache-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 →