Send a message to a sitter on Rover. Requires being logged in.
AI agents use message_sitter to create or update resources in Rover MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rover MCP Server environment.
The tool creates new data (messages) in the Rover system. While messaging is generally low-risk, the medium severity accounts for potential misuse such as sending fraudulent communications, impersonation, or harassment to sitters, which could have tangible consequences for user relationships and platform trust.
From the tool's definition Tool description states 'Send a message to a sitter on Rover', which creates new communication data on the platform. This is a write operation that creates reversible artifacts (messages can typically be deleted or edited on messaging platforms).
Attacks that exploit this kind of access
Send a message to a sitter on Rover. Requires being logged in. It is categorised as a Write tool in the Rover MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rover MCP Server MCP server in PolicyLayer and add a rule for message_sitter: 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 Rover MCP Server. Nothing to install.
message_sitter 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 message_sitter 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 message_sitter. 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.
message_sitter is provided by the Rover MCP Server MCP server (markswendsen-code/mcp-rover). 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 →