AI agents call get_webhooks to retrieve information from Hevy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it queries and retrieves existing webhook data without modification. However, severity is elevated to 'high' because webhooks in fitness apps may contain sensitive configuration details, callback URLs, authentication tokens, or subscription preferences that could reveal system architecture, integrations, or enable an attacker to identify exploit targets.
From the tool's definition Tool name is 'get_webhooks' which retrieves/lists webhook subscriptions with no side effects. Description states 'List all active webhook subscriptions' confirming read-only retrieval operation.
Attacks that exploit this kind of access
List all active webhook subscriptions. It is categorised as a Read tool in the Hevy MCP Server, which means it retrieves data without modifying state.
Register the Hevy MCP server in PolicyLayer and add a rule for get_webhooks: 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 Hevy. Nothing to install.
get_webhooks 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_webhooks 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_webhooks. 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_webhooks is provided by the Hevy MCP server (srdjancodes/hevy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_webhooks is one line of Hevy's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →