Reject an official mirror queue entry. This is an async operation that enqueues a background job. This action: 1. Marks the queue entry as rejected 2. Enqueues a background job to process the rejection 3. The entry will not be linked to any MCP server Important: This is an asynchronous operation....
AI agents use reject_official_mirror_queue_item to create or update resources in Langfuse Observability — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Langfuse Observability environment.
The tool modifies queue entry state (marking as rejected) and triggers a background job for processing. This is a Write operation because it changes data state reversibly—rejected entries can potentially be resubmitted or reviewed. It does not permanently delete data (would be Destructive) nor does it execute arbitrary code (would be Execute).
From the tool's definition Marks the queue entry as rejected and enqueues a background job to process the rejection. The entry will not be linked to any MCP server. This modifies state of queue entries but does not permanently delete them.
Attacks that exploit this kind of access
Reject an official mirror queue entry. This is an async operation that enqueues a background job. This action: 1. Marks the queue entry as rejected 2. Enqueues a background job to process the rejection 3. The entry will not be linked to any MCP server Important: This is an asynchronous operation. The response indicates the job was enqueued, not that the rejection is complete. Use get_official_mirror_queue_item to poll for completion. Use cases: - Reject submissions that don. It is categorised as a Write tool in the Langfuse Observability MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Langfuse Observability MCP server in PolicyLayer and add a rule for reject_official_mirror_queue_item: 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 Observability. Nothing to install.
reject_official_mirror_queue_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the reject_official_mirror_queue_item 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 reject_official_mirror_queue_item. 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.
reject_official_mirror_queue_item is provided by the Langfuse Observability MCP server (langfuse-observability-mcp-server). 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 →