Cancel a running Proctor exam. Stops an exam that is currently executing on a Fly machine. This is useful when you need to abort a test that is taking too long or encountering issues. Returns: - Result object indicating the cancellation status Use cases: - Stop a stuck or slow exam - Cancel a tes...
AI agents invoke cancel_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.
This tool triggers an external operation (stopping/cancelling a running process on a Fly machine). It is not purely destructive (it doesn't delete data or the machine itself — 'the machine may still need to be destroyed separately'), but it executes an action that terminates a running process, making Execute the most appropriate category.
From the tool's definition Stops an exam that is currently executing on a Fly machine. This is useful when you need to abort a test that is taking too long or encountering issues.
Attacks that exploit this kind of access
Cancel a running Proctor exam. Stops an exam that is currently executing on a Fly machine. This is useful when you need to abort a test that is taking too long or encountering issues. Returns: - Result object indicating the cancellation status Use cases: - Stop a stuck or slow exam - Cancel a test started with wrong parameters - Free up resources for other tests - Gracefully terminate a running exam before destroying the machine Note: - The exam must be currently running on the specified machine - After cancellation, the machine may still need to be destroyed separately - Results from a cancelled exam will not be saved automatically. 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.
Register the Langfuse Observability MCP server in PolicyLayer and add a rule for cancel_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.
cancel_exam is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cancel_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.
Set action: deny in the PolicyLayer policy for cancel_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.
cancel_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.
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 →