AI agents call search_walkers to retrieve information from Mcp Wag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available or user-accessible walker information from wagwalking.com without creating, modifying, deleting, or executing any side effects. It is purely informational, making it a Read category risk with low severity—misuse would only expose existing data, not cause financial or operational damage.
From the tool's definition Tool description states it 'Search for available dog walkers' and 'Returns walker cards with name, rating, price, and availability.' The verb 'search' and the focus on returning information without modifying any data indicates a read-only operation.
Attacks that exploit this kind of access
Search for available dog walkers on wagwalking.com by location, date, and service type. Returns walker cards with name, rating, price, and availability. It is categorised as a Read tool in the Mcp Wag MCP Server, which means it retrieves data without modifying state.
Register the Mcp Wag MCP server in PolicyLayer and add a rule for search_walkers: 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 Mcp Wag. Nothing to install.
search_walkers 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 search_walkers 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 search_walkers. 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.
search_walkers is provided by the Mcp Wag MCP server (markswendsen-code/mcp-wag). 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 →