AI agents use install_mcp to create or update resources in ScoutMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ScoutMCP environment.
An AI agent can call install_mcp faster than any human can review — one bad instruction and it creates or modifies resources in ScoutMCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
install_mcp. It is categorised as a Write tool in the ScoutMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scout MCP server in PolicyLayer and add a rule for install_mcp: 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 ScoutMCP. Nothing to install.
install_mcp 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 install_mcp 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 install_mcp. 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.
install_mcp is provided by the Scout MCP server (yudduy/scoutmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.