Create or update a meal within a nutrition day.
AI agents use upsert_meal to create or update resources in MCP Logger — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Logger environment.
This tool creates new meal records or modifies existing ones in the fitness tracking database, which are standard Write operations. The changes are reversible (meals can be deleted or updated again), and the blast radius is moderate—an AI agent could log incorrect meals or nutritional data, affecting user health tracking accuracy, but cannot permanently destroy data or trigger financial transactions.
From the tool's definition Tool name 'upsert_meal' and description 'Create or update a meal within a nutrition day' explicitly indicate reversible creation or modification of data.
Attacks that exploit this kind of access
Create or update a meal within a nutrition day. It is categorised as a Write tool in the MCP Logger MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Logger MCP server in PolicyLayer and add a rule for upsert_meal: 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 MCP Logger. Nothing to install.
upsert_meal 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 upsert_meal 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 upsert_meal. 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.
upsert_meal is provided by the MCP Logger MCP server (johnzolton/mcp-logger). 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 →