AI agents use create_custom_food to create or update resources in Garmin MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Garmin MCP Server environment.
The tool creates new custom food entries in Garmin Connect, which modifies user data reversibly. This is a Write operation. Severity is medium because misuse could add incorrect nutritional data affecting the user's fitness tracking, but the data can be edited or deleted. Confidence is reduced from high to 0.75 due to the empty description.
From the tool's definition Tool name 'create_custom_food' indicates creation of a new data entry. Server description confirms the server exposes fitness and health data to Claude.
Documented attack patterns abuse exactly the kind of access create_custom_food gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Garmin MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_custom_food:
{
"version": "1",
"default": "deny",
"tools": {
"create_custom_food": {
"limits": [
{
"counter": "create_custom_food_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} create_custom_food stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
create_custom_food. It is categorised as a Write tool in the Garmin MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Garmin MCP Server MCP server in PolicyLayer and add a rule for create_custom_food: 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 Garmin MCP Server. Nothing to install.
create_custom_food 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 create_custom_food 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 create_custom_food. 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.
create_custom_food is provided by the Garmin MCP Server MCP server (taxuspt/garmin_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 126 Garmin MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
126 Garmin MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.