AI agents call cicd_github_workflow_runs to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical workflow run information from GitHub Actions. It performs a read-only query operation that does not create, modify, delete, or execute any resources. The blast radius of misuse is minimal—an agent could enumerate CI/CD pipeline execution history, which may expose metadata about deployments or build artifacts, but cannot independently trigger workflows or modify infrastructure.
From the tool's definition Tool name includes 'List' verb and description states 'List recent workflow runs' — a query operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
List recent workflow runs for a GitHub Actions workflow. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for cicd_github_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 Infra Ops. Nothing to install.
cicd_github_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 cicd_github_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 cicd_github_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.
cicd_github_workflow_runs is provided by the Infra Ops MCP server (skyvanguard/infra-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →