AI agents call read_rtt to retrieve information from Jlink without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads from RTT (Real-Time Transfer) buffers, which are debug output logs from microcontroller firmware. Reading debug logs is a passive operation that retrieves data without altering system state, making it a Read category tool. The low severity reflects that RTT buffers typically contain non-sensitive diagnostic information. No destructive, write, execute, or financial operations are performed.
From the tool's definition Tool name 'read_rtt' and description '读取 SEGGER RTT（Real Time Transfer）缓冲区内容' (read SEGGER RTT buffer contents) indicate data retrieval without modification or side effects.
Attacks that exploit this kind of access
读取 SEGGER RTT（Real Time Transfer）缓冲区内容。. It is categorised as a Read tool in the Jlink MCP Server, which means it retrieves data without modifying state.
Register the Jlink MCP server in PolicyLayer and add a rule for read_rtt: 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 Jlink. Nothing to install.
read_rtt 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_rtt 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_rtt. 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_rtt is provided by the Jlink MCP server (xun123456/jlink-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 →