List automation runs for a user, optionally filtered by status
AI agents call get_automation_runs to retrieve information from MCP Automation Service without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns automation run records without modifying, creating, or deleting data. It is a pure read operation that retrieves metadata about past automation executions. The filtering by status does not change underlying data.
From the tool's definition Tool description states 'List automation runs for a user, optionally filtered by status' — a retrieval operation with no side effects or mutations.
Attacks that exploit this kind of access
List automation runs for a user, optionally filtered by status. It is categorised as a Read tool in the MCP Automation Service MCP Server, which means it retrieves data without modifying state.
Register the MCP Automation Service MCP server in PolicyLayer and add a rule for get_automation_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 MCP Automation Service. Nothing to install.
get_automation_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 get_automation_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 get_automation_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.
get_automation_runs is provided by the MCP Automation Service MCP server (shukurlukerem/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 →