java_jfr_start
AI agents invoke java_jfr_start to trigger actions in Heap Seance. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
JFR recording startup is an Execute operation because it triggers real-time instrumentation of a JVM process with observable side effects. While not irreversible (recordings can be stopped), it actively runs code/instrumentation on the target process. The empty description lowers confidence slightly, but the tool name is sufficiently explicit.
From the tool's definition Tool name 'java_jfr_start' indicates initiation of Java Flight Recorder (JFR) recording. JFR is a runtime profiling and diagnostics tool that actively instruments and monitors a running JVM process.
Attacks that exploit this kind of access
java_jfr_start. It is categorised as a Execute tool in the Heap Seance MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Heap Seance MCP server in PolicyLayer and add a rule for java_jfr_start: 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 Heap Seance. Nothing to install.
java_jfr_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the java_jfr_start 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 java_jfr_start. 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.
java_jfr_start is provided by the Heap Seance MCP server (segfaultsorcerer/heap-seance). 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 →