add_inline_policy
AI agents use add_inline_policy to create or update resources in AWS IoT SiteWise MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AWS IoT SiteWise MCP Server environment.
The tool adds an inline policy, which is a reversible Write operation that creates or modifies IAM permissions. While not immediately destructive, misconfigured policies could grant excessive permissions to IoT resources. Severity is high because policy misconfigurations can lead to unauthorized access to industrial data/devices, but the operation itself is not irreversible (policies can be detached/updated).
From the tool's definition Tool name 'add_inline_policy' indicates creation of an IAM policy. Combined with AWS IoT SiteWise context, this creates or modifies access control policies.
Attacks that exploit this kind of access
add_inline_policy. It is categorised as a Write tool in the AWS IoT SiteWise MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AWS IoT SiteWise MCP Server MCP server in PolicyLayer and add a rule for add_inline_policy: 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 AWS IoT SiteWise MCP Server. Nothing to install.
add_inline_policy 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 add_inline_policy 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 add_inline_policy. 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.
add_inline_policy is provided by the AWS IoT SiteWise MCP Server MCP server (awslabs.aws-iot-sitewise-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.