java_mat_suspects
AI agents call java_mat_suspects to retrieve information from Heap Seance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
MAT suspects analysis is a read-only diagnostic operation that examines heap dumps to identify potential memory leaks. It retrieves and correlates existing data without modifying the target JVM, creating resources, or executing arbitrary code.
From the tool's definition Tool name 'java_mat_suspects' and sibling tools in the heap-seance server context (java_class_histogram, java_heap_dump, java_jfr_summary, java_async_alloc_profile) are all diagnostic/analysis tools for Java memory investigation.
Attacks that exploit this kind of access
java_mat_suspects. It is categorised as a Read tool in the Heap Seance MCP Server, which means it retrieves data without modifying state.
Register the Heap Seance MCP server in PolicyLayer and add a rule for java_mat_suspects: 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_mat_suspects 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 java_mat_suspects 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_mat_suspects. 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_mat_suspects 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 →