Delete a specific trace. This action is irreversible.
AI agents call deleteTrace to permanently remove resources in Langfuse Mcp Extended — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes trace data without the ability to recover it. This is a destructive operation that cannot be undone. While the blast radius is limited to trace data (not critical system operations or financial impacts), the irreversible nature and potential loss of observability/audit data justifies 'high' severity.
From the tool's definition Tool description states: 'Delete a specific trace. This action is irreversible.' The verb 'Delete' combined with 'irreversible' explicitly indicates irreversible data removal.
Attacks that exploit this kind of access
Delete a specific trace. This action is irreversible. It is categorised as a Destructive tool in the Langfuse Mcp Extended MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Langfuse Mcp Extended MCP server in PolicyLayer and add a rule for deleteTrace: 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 Langfuse Mcp Extended. Nothing to install.
deleteTrace is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the deleteTrace 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 deleteTrace. 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.
deleteTrace is provided by the Langfuse Mcp Extended MCP server (langfuse-mcp-extended). 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 →