Get details about a specific DAG run.
AI agents call get_dag_run to retrieve information from MWAA 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 and queries information about DAG (Directed Acyclic Graph) run details without side effects. It falls squarely into the Read category as it accesses monitoring/observability data. The blast radius is low because it only exposes historical or real-time run metadata, not control plane operations or data modification capabilities.
From the tool's definition Tool name 'get_dag_run' and description 'Get details about a specific DAG run' indicate retrieval of workflow execution information.
Attacks that exploit this kind of access
Get details about a specific DAG run. It is categorised as a Read tool in the MWAA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MWAA MCP Server MCP server in PolicyLayer and add a rule for get_dag_run: 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 MWAA MCP Server. Nothing to install.
get_dag_run 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_dag_run 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_dag_run. 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_dag_run is provided by the MWAA MCP Server MCP server (paschmaria/mwaa-mcp-server). 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 →