AI agents use rate_walker to create or update resources in Mcp Wag — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Wag environment.
This tool creates or modifies data (a review/rating and optionally a tip) in a reversible manner. Reviews can be edited or deleted, and tips represent normal service payment rather than irreversible financial commitment.
From the tool's definition Tool description states it will 'Rate and review a walker' and 'add a tip', which are reversible modifications to data (reviews can be edited/deleted, tips are transactional but not irreversible transfers).
Attacks that exploit this kind of access
Rate and review a walker after a completed walk on wagwalking.com. Optionally add a tip. Requires WAG_EMAIL and WAG_PASSWORD. It is categorised as a Write tool in the Mcp Wag MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Wag MCP server in PolicyLayer and add a rule for rate_walker: 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.
rate_walker 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 rate_walker 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 rate_walker. 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.
rate_walker 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 →