param_get
AI agents call param_get to retrieve information from Flex Sensor Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' verb conventionally indicates retrieval without modification. No side effects or destructive capability are implied. In the context of a COMSOL simulation server, parameter retrieval is a foundational read operation. Confidence is reduced from 0.9 to 0.82 due to the empty description, which leaves some ambiguity about whether this could retrieve sensitive simulation data or internal state.
From the tool's definition Tool name 'param_get' indicates a getter function that retrieves parameters. The naming convention strongly suggests read-only data retrieval.
Attacks that exploit this kind of access
param_get. It is categorised as a Read tool in the Flex Sensor Agent MCP Server, which means it retrieves data without modifying state.
Register the Flex Sensor Agent MCP server in PolicyLayer and add a rule for param_get: 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 Flex Sensor Agent. Nothing to install.
param_get 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 param_get 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 param_get. 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.
param_get is provided by the Flex Sensor Agent MCP server (tonghui666/flex-sensor-agent-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 →