Delete a trace and all its associated observations.
AI agents call delete_trace to permanently remove resources in Langfuse Mcp Python — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes traces and their associated observations from the system. Deletion is an irreversible destructive action with no recovery mechanism described. The blast radius is high because an AI agent could inadvertently delete critical monitoring and observability records needed for auditing, debugging, or compliance.
From the tool's definition 'Delete a trace and all its associated observations' — the tool irreversibly removes data and cannot be undone.
Attacks that exploit this kind of access
Delete a trace and all its associated observations. It is categorised as a Destructive tool in the Langfuse Mcp Python MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Langfuse Mcp Python MCP server in PolicyLayer and add a rule for delete_trace: 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 Python. Nothing to install.
delete_trace 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 delete_trace 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 delete_trace. 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.
delete_trace is provided by the Langfuse Mcp Python MCP server (log-logn/langfuse-mcp-python). 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 →