cancel_job · Flint Slating MCP: Risk & Policy

WHAT IT DOES

What cancel_job does on Flint Slating

AI agents invoke cancel_job to trigger actions in Flint Slating. 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 cancel_job needs a policy

Cancelling a running job terminates an in-progress operation, which is an external action with real side effects (the job stops executing). It is not a simple read, nor does it delete stored data outright, but it does trigger a state change in the system. This falls under Execute as it affects the runtime behavior of an ongoing process.

From the tool's definition cancel_job — 'Cooperatively cancel a running job'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cancel_job Rate-limited

cancel_job 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": {
    "cancel_job": {
      "limits": [
        {
          "counter": "cancel_job_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 Flint Slating, so you can run agents against it safely.

FAQ

Questions about cancel_job

What does the cancel_job tool do? +

Cooperatively cancel a running job. Returns {ok: bool}. It is categorised as a Execute tool in the Flint Slating MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cancel_job? +

Register the Flint Slating MCP server in PolicyLayer and add a rule for cancel_job: 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 Flint Slating. Nothing to install.

What risk level is cancel_job? +

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

Can I rate-limit cancel_job? +

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

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

cancel_job is provided by the Flint Slating MCP server (parkviewlab/flint-slating). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.