workflows_step_failed · Slack MCP: Risk & Policy

WHAT IT DOES

What workflows_step_failed does on Slack

AI agents invoke workflows_step_failed to trigger actions in Slack. 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 workflows_step_failed needs a policy

Marking a workflow step as failed is an external operation that affects the execution state of a running workflow. It can trigger error-handling paths, halt dependent steps, or cause cascading failures across automated processes. This is not a simple data write — it drives runtime behavior, making Execute the appropriate category. Severity is high because misuse could disrupt business-critical automated workflows.

From the tool's definition "Indicate a workflow step has failed" — this triggers a state change in an external workflow execution, signaling failure and potentially causing workflow branching, error handlers, retries, or halting downstream steps.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

workflows_step_failed Rate-limited

workflows_step_failed 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": {
    "workflows_step_failed": {
      "limits": [
        {
          "counter": "workflows_step_failed_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 Slack, so you can run agents against it safely.

FAQ

Questions about workflows_step_failed

What does the workflows_step_failed tool do? +

Indicate a workflow step has failed. It is categorised as a Execute tool in the Slack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on workflows_step_failed? +

Register the Slack MCP server in PolicyLayer and add a rule for workflows_step_failed: 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 Slack. Nothing to install.

What risk level is workflows_step_failed? +

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

Can I rate-limit workflows_step_failed? +

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

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

workflows_step_failed is provided by the Slack MCP server (karbassi/slack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.