AI agents call find_spots 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 appears to search for or retrieve surf spot information based on criteria. It has no side effects—it does not create, modify, delete, or execute external operations. The name 'find_spots' and its place among other Read-category tools (list_regions, list_spots, get_spot_info, get_forecast, get_tides) confirms it is a Read operation.
From the tool's definition Tool name is 'find_spots' and the server description indicates it is part of a suite of tools for 'querying surf spot data and searching spots' with tools that 'list regions, spots, get spot info, find spots by criteria'.
Attacks that exploit this kind of access
find_spots. 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 find_spots: 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.
find_spots 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 find_spots 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 find_spots. 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.
find_spots 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 →