AI agents call check_network to retrieve information from Memory Shell Detector MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Network connectivity checking is a non-destructive diagnostic operation that queries and reports network status. It has no side effects, does not execute arbitrary commands, and does not modify or delete data. This falls squarely in the Read category. Severity is low because the blast radius of misuse is minimal—an agent cannot cause meaningful harm by checking network connectivity.
From the tool's definition Tool name is 'check_network' with description 'checks network connectivity' (translated from Chinese: 检测网络连通性). The description indicates a diagnostic query operation that retrieves network status information without modifying system state.
Documented attack patterns abuse exactly the kind of access check_network gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Shell Detector MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for check_network:
{
"version": "1",
"default": "deny",
"tools": {
"check_network": {}
}
}check_network is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
检测网络连通性. It is categorised as a Read tool in the Memory Shell Detector MCP MCP Server, which means it retrieves data without modifying state.
Register the Memory Shell Detector MCP server in PolicyLayer and add a rule for check_network: 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 Memory Shell Detector MCP. Nothing to install.
check_network 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 check_network 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 check_network. 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.
check_network is provided by the Memory Shell Detector MCP server (ruoji6/memory-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Shell Detector MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Memory Shell Detector MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.