update_agent_runtime
AI agents use update_agent_runtime 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 name 'update_agent_runtime' implies a Write operation that modifies an existing agent runtime. However, the empty description significantly lowers confidence. Given the context of AWS IoT SiteWise, this likely updates runtime settings for an IoT agent, which is a high-severity Write operation as misconfiguration could disrupt IoT data collection pipelines.
From the tool's definition Tool name 'update_agent_runtime' suggests modifying an agent runtime configuration; description is empty and uninformative.
Attacks that exploit this kind of access
update_agent_runtime. 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 update_agent_runtime: 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.
update_agent_runtime 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 update_agent_runtime 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 update_agent_runtime. 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.
update_agent_runtime 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.