approve_mirror_no_modify · Langfuse Observability MCP

WHAT IT DOES

What approve_mirror_no_modify does on Langfuse Observability

AI agents use approve_mirror_no_modify 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.

WHY IT NEEDS A POLICY

Why approve_mirror_no_modify needs a policy

This is a Write operation because it modifies the state of a queue entry (marking it as approved), which is a reversible administrative action. However, it is intentionally limited to not apply changes to the linked server, reducing the blast radius compared to a tool that would actually update server configuration.

From the tool's definition The tool 'approve_mirror_no_modify' performs a state change by marking a queue entry as approved, which is a reversible modification to the queue entry's status.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_mirror_no_modify Rate-limited

approve_mirror_no_modify stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "approve_mirror_no_modify": {
      "limits": [
        {
          "counter": "approve_mirror_no_modify_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Langfuse Observability, so you can run agents against it safely.

FAQ

Questions about approve_mirror_no_modify

What does the approve_mirror_no_modify tool do? +

Approve an official mirror queue entry without modifying the linked MCP server. This is a synchronous operation. This action: 1. Marks the queue entry as approved 2. Does NOT update the linked MCP server with mirror data 3. Requires the queue entry to already be linked to a server Use this when: - The queue entry shows an update (pending_update) but you want to acknowledge it without applying changes - The existing server data is correct and doesn. 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.

How do I enforce a policy on approve_mirror_no_modify? +

Register the Langfuse Observability MCP server in PolicyLayer and add a rule for approve_mirror_no_modify: 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.

What risk level is approve_mirror_no_modify? +

approve_mirror_no_modify is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit approve_mirror_no_modify? +

Yes. Add a rate_limit block to the approve_mirror_no_modify 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.

How do I block approve_mirror_no_modify completely? +

Set action: deny in the PolicyLayer policy for approve_mirror_no_modify. 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.

What MCP server provides approve_mirror_no_modify? +

approve_mirror_no_modify 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.