Generate minidump on demand
AI agents invoke create_minidump to trigger actions in MCP Debug Server. 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.
Creating a minidump involves executing a privileged OS-level operation that captures process memory state and writes it to disk. While not purely destructive (the process continues), it can expose sensitive memory contents (credentials, keys, PII) and constitutes an active execution of a system-level operation.
From the tool's definition 'Generate minidump on demand' — actively triggers a dump of process memory to disk
Attacks that exploit this kind of access
Generate minidump on demand. It is categorised as a Execute tool in the MCP Debug Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Debug Server MCP server in PolicyLayer and add a rule for create_minidump: 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 MCP Debug Server. Nothing to install.
create_minidump 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 create_minidump 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 create_minidump. 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.
create_minidump is provided by the MCP Debug Server MCP server (nickzer0/mcp-debugserver). 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 →