get_agent_runtime
AI agents call get_agent_runtime to retrieve information from AWS IoT SiteWise MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming convention 'get_*' is strongly associated with read operations that retrieve data without side effects. However, confidence is moderate (0.6) rather than high because the description is empty, leaving some ambiguity about the tool's exact function. If 'agent_runtime' refers to querying operational metrics or status of an AWS IoT SiteWise agent, this is consistent with a Read classification.
From the tool's definition Tool name 'get_agent_runtime' suggests retrieval of runtime information or status data about an agent, with no indication of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
get_agent_runtime. It is categorised as a Read tool in the AWS IoT SiteWise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS IoT SiteWise MCP Server MCP server in PolicyLayer and add a rule for get_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.
get_agent_runtime 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 get_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 get_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.
get_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.