submit_score · Langfuse Mcp Python MCP: Risk & Policy

WHAT IT DOES

What submit_score does on Langfuse Mcp Python

AI agents use submit_score 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 submit_score needs a policy

This tool creates or modifies evaluation score records associated with traces or observations in Langfuse. While it records data (scores), it is reversible and does not delete, destroy, or execute arbitrary code. It does not move money or have financial implications.

From the tool's definition Tool description states 'Submit an evaluation score for a trace or observation.' The verb 'submit' indicates creating or modifying data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

submit_score Rate-limited

submit_score 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": {
    "submit_score": {
      "limits": [
        {
          "counter": "submit_score_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 submit_score

What does the submit_score tool do? +

Submit an evaluation score for 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 submit_score? +

Register the Langfuse Mcp Python MCP server in PolicyLayer and add a rule for submit_score: 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 submit_score? +

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

Can I rate-limit submit_score? +

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

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

submit_score 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.