rerun_workflow · GitHub Actions MCP Server MCP

WHAT IT DOES

What rerun_workflow does on GitHub Actions MCP Server

AI agents invoke rerun_workflow to trigger actions in GitHub Actions MCP Server. 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 rerun_workflow needs a policy

This tool triggers external operations (GitHub Actions CI/CD pipeline execution) whose side effects are determined by the workflow definition and runtime environment. While not directly destructive or financial, workflow execution can modify repositories, deploy code, run tests, or interact with external systems.

From the tool's definition Tool name 'rerun_workflow' and description 'Re-run a workflow run' indicate this triggers execution of an existing GitHub Actions workflow.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rerun_workflow Rate-limited

rerun_workflow 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": {
    "rerun_workflow": {
      "limits": [
        {
          "counter": "rerun_workflow_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 GitHub Actions MCP Server, so you can run agents against it safely.

FAQ

Questions about rerun_workflow

What does the rerun_workflow tool do? +

Re-run a workflow run. It is categorised as a Execute tool in the GitHub Actions MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on rerun_workflow? +

Register the GitHub Actions MCP Server MCP server in PolicyLayer and add a rule for rerun_workflow: 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 GitHub Actions MCP Server. Nothing to install.

What risk level is rerun_workflow? +

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

Can I rate-limit rerun_workflow? +

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

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

rerun_workflow is provided by the GitHub Actions MCP Server MCP server (onemarc/github-actions-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.