Critical-risk tools in Langfuse Mcp Python

Critical severity Langfuse Mcp Python MCP Server 7 of 40 tools

7 of the 40 tools in Langfuse Mcp Python are classified as critical risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at critical risk

delete_annotation_queue Destructive

Delete an annotation queue.
delete_blob_storage_integration Destructive

Delete a blob storage integration by ID.
delete_dataset Destructive

Delete a dataset and all its items.
delete_model Destructive

Delete a custom model configuration.
delete_project Destructive

Delete a project by ID (requires organization-scoped API key).
delete_prompt Destructive

Delete a specific prompt version or all versions.
delete_trace Destructive

Delete a trace and all its associated observations.

Attacks that target this class

Critical-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

Destructive Action Autonomy
Privilege escalation via admin-only tools
Data exfiltration via tool chaining
Runaway Tool Loops

Critical-risk tools in Langfuse Mcp Python

Tools at critical risk

Attacks that target this class

More on Langfuse Mcp Python

Enforce policy on every Langfuse Mcp Python tool call.