Deploy MokuConfig to connected device
AI agents use push_config to create or update resources in Moku MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moku MCP Server environment.
This tool modifies device configuration settings on a connected Moku device. While configuration changes are not irreversible deletions (which would be Destructive), they are write operations that alter device state. The severity is medium because misconfigured settings could disrupt device operation or connected systems, but the changes appear to be reversible through subsequent configurations.
From the tool's definition Tool name 'push_config' and description 'Deploy MokuConfig to connected device' indicate modification of device configuration state. The term 'deploy' suggests applying changes to the device.
Attacks that exploit this kind of access
Deploy MokuConfig to connected device. It is categorised as a Write tool in the Moku MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Moku MCP Server MCP server in PolicyLayer and add a rule for push_config: 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 Moku MCP Server. Nothing to install.
push_config 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 push_config 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 push_config. 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.
push_config is provided by the Moku MCP Server MCP server (sealablab/moku-mcp). 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 →