AI agents call get_tides to retrieve information from Surf without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tide information for surf forecasting purposes. It queries data without modifying, deleting, or executing external operations. The lack of description slightly reduces confidence, but the server's read-only nature and naming pattern strongly indicate a retrieval function.
From the tool's definition Tool name 'get_tides' and server context (surf-mcp-server for querying surf spot data) indicate this retrieves tide information.
Attacks that exploit this kind of access
get_tides. It is categorised as a Read tool in the Surf MCP Server, which means it retrieves data without modifying state.
Register the Surf MCP server in PolicyLayer and add a rule for get_tides: 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 Surf. Nothing to install.
get_tides 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_tides 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_tides. 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_tides is provided by the Surf MCP server (steph76k/surf-mcp-server). 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 →