retry_task · Ebb Ai MCP: Risk & Policy

WHAT IT DOES

What retry_task does on Ebb Ai

AI agents invoke retry_task to trigger actions in Ebb Ai. 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 retry_task needs a policy

The tool re-dispatches (re-executes) a previously failed task, triggering an external LLM provider call (Anthropic/OpenAI Batch API). This is an Execute action since it triggers an external operation. Severity is medium because misuse could cause unintended repeated API calls and associated costs, though it is not directly financial or destructive.

From the tool's definition Re-dispatch a failed provider-call task

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retry_task Rate-limited

retry_task 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": {
    "retry_task": {
      "limits": [
        {
          "counter": "retry_task_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 Ebb Ai, so you can run agents against it safely.

FAQ

Questions about retry_task

What does the retry_task tool do? +

Re-dispatch a failed provider-call task. Only valid when the task. It is categorised as a Execute tool in the Ebb Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on retry_task? +

Register the Ebb Ai MCP server in PolicyLayer and add a rule for retry_task: 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 Ebb Ai. Nothing to install.

What risk level is retry_task? +

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

Can I rate-limit retry_task? +

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

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

retry_task is provided by the Ebb Ai MCP server (vitalini/ebb-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.