add_comment · Langfuse Mcp Python MCP: Risk & Policy

WHAT IT DOES

What add_comment does on Langfuse Mcp Python

AI agents use add_comment to create or update resources in Langfuse Mcp Python — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Langfuse Mcp Python environment.

WHY IT NEEDS A POLICY

Why add_comment needs a policy

Adding a comment creates new metadata/annotation on existing traces or observations without modifying the core data, deleting anything, executing code, or moving funds. This is a straightforward Write operation with minimal blast radius—comments can be edited or deleted later. The low severity reflects that erroneous comments have limited impact on system functionality.

From the tool's definition Tool description states it 'Add a comment' which creates new data (a comment) in the system. The verb 'add' indicates creation of a reversible change.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_comment Rate-limited

add_comment 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": {
    "add_comment": {
      "limits": [
        {
          "counter": "add_comment_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 Mcp Python, so you can run agents against it safely.

FAQ

Questions about add_comment

What does the add_comment tool do? +

Add a comment to a trace or observation. It is categorised as a Write tool in the Langfuse Mcp Python MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_comment? +

Register the Langfuse Mcp Python MCP server in PolicyLayer and add a rule for add_comment: 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.

What risk level is add_comment? +

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

Can I rate-limit add_comment? +

Yes. Add a rate_limit block to the add_comment 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 add_comment completely? +

Set action: deny in the PolicyLayer policy for add_comment. 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 add_comment? +

add_comment 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.