Read JS220 general-purpose input pin state as a 32-bit value and decoded pins.
AI agents call read_gpi to retrieve information from Joulescope without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the current state of hardware inputs without modifying any state or triggering external actions. Reading GPIO input is a passive observation operation typical of measurement and monitoring scenarios, consistent with the JouleScope's purpose as a precision energy analyzer. No data is created, modified, deleted, or any code executed.
From the tool's definition The tool 'read_gpi' is explicitly described as reading the JS220 general-purpose input pin state, returning a 32-bit value and decoded pins. The verb 'read' combined with 'input pin state' indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Read JS220 general-purpose input pin state as a 32-bit value and decoded pins. It is categorised as a Read tool in the Joulescope MCP Server, which means it retrieves data without modifying state.
Register the Joulescope MCP server in PolicyLayer and add a rule for read_gpi: 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 Joulescope. Nothing to install.
read_gpi 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 read_gpi 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 read_gpi. 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.
read_gpi is provided by the Joulescope MCP server (juanqui/joulescope-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 →