AI agents call list_workflow_runs to retrieve information from GitHub Actions MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists workflow runs without modifying, executing, or deleting anything. It has no side effects and is a standard query operation on GitHub's API. The blast radius is minimal—an AI agent misusing it could only enumerate runs, not cause operational impact.
From the tool's definition Tool name 'list_workflow_runs' indicates retrieval/querying of workflow run data. Server description confirms it 'enabling AI assistants to manage GitHub Actions workflows by providing tools for listing, viewing, triggering, canceling, and rerunning…
Documented attack patterns abuse exactly the kind of access list_workflow_runs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GitHub Actions MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_workflow_runs:
{
"version": "1",
"default": "deny",
"tools": {
"list_workflow_runs": {}
}
}list_workflow_runs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_workflow_runs. It is categorised as a Read tool in the GitHub Actions MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub Actions MCP Server MCP server in PolicyLayer and add a rule for list_workflow_runs: 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.
list_workflow_runs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_workflow_runs 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 list_workflow_runs. 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.
list_workflow_runs is provided by the GitHub Actions MCP Server MCP server (ko1ynnky/github-actions-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GitHub Actions MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 GitHub Actions MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.