Get water consumption for a specific day.
AI agents call get_water_intake to retrieve information from Myfitnesspal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical water intake data from MyFitnessPal without creating, modifying, deleting, or executing any operations. It is purely informational. The blast radius of misuse is minimal—an AI agent could retrieve a user's water intake logs but cannot cause financial, destructive, or operational harm with this data access alone.
From the tool's definition Tool name 'get_water_intake' and description 'Get water consumption for a specific day' indicate a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Get water consumption for a specific day. It is categorised as a Read tool in the Myfitnesspal MCP Server, which means it retrieves data without modifying state.
Register the Myfitnesspal MCP server in PolicyLayer and add a rule for get_water_intake: 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 Myfitnesspal. Nothing to install.
get_water_intake 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 get_water_intake 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 get_water_intake. 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.
get_water_intake is provided by the Myfitnesspal MCP server (linares222/mcp-myfitnesspal). 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 →