save_insight
AI agents use save_insight to create or update resources in Wellness Planner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wellness Planner environment.
The name 'save_insight' indicates a write operation that persists insights to the database. Given the sibling tools (get_insights, propose_schedule) and SQLite backend, this tool likely creates or updates records. Without an explicit description, confidence is reduced, but the naming convention and server architecture point to Write rather than Read.
From the tool's definition Tool name 'save_insight' implies persistence of data. The server description mentions 'task management' and 'local SQLite database', suggesting tools can modify stored state. No description provided to confirm scope.
Attacks that exploit this kind of access
save_insight. It is categorised as a Write tool in the Wellness Planner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wellness Planner MCP server in PolicyLayer and add a rule for save_insight: 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 Wellness Planner. Nothing to install.
save_insight is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_insight 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 save_insight. 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.
save_insight is provided by the Wellness Planner MCP server (rwking/wellness_planner). 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 →