run_exam · Langfuse Observability MCP: Risk & Policy

WHAT IT DOES

What run_exam does on Langfuse Observability

AI agents invoke run_exam to trigger actions in Langfuse Observability. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_exam needs a policy

This tool executes an exam against an MCP server, which involves running code/operations with effects determined by user-supplied parameters (exam specification, runtime, MCP config). This is an Execute category tool because it triggers operations on external systems. Severity is high due to potential for misconfiguration or malicious exam payloads to affect MCP server behavior or state.

From the tool's definition Tool name 'run_exam' and description states it 'Execute[s] a Proctor exam against an MCP server' and 'Runs the specified exam using the provided runtime and MCP configuration.' The verb 'Execute' and 'Runs' indicate this triggers external operations whose…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_exam Rate-limited

run_exam stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_exam": {
      "limits": [
        {
          "counter": "run_exam_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 run_exam

What does the run_exam tool do? +

Execute a Proctor exam against an MCP server. Runs the specified exam using the provided runtime and MCP configuration. The exam tests the MCP server. It is categorised as a Execute tool in the Langfuse Observability MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_exam? +

Register the Langfuse Observability MCP server in PolicyLayer and add a rule for run_exam: 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 run_exam? +

run_exam is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_exam? +

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

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

run_exam 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.