Create a CLI token for executing Airflow CLI commands.
AI agents invoke create_cli_token to trigger actions in MWAA 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.
A CLI token enables execution of arbitrary Airflow CLI commands, which can trigger DAG runs, modify configurations, manage connections/variables, and perform other operations. The token itself is a credential enabler for Execute-level actions.
From the tool's definition Create a CLI token for executing Airflow CLI commands
Attacks that exploit this kind of access
Create a CLI token for executing Airflow CLI commands. It is categorised as a Execute tool in the MWAA MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MWAA MCP Server MCP server in PolicyLayer and add a rule for create_cli_token: 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.
create_cli_token is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_cli_token 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 create_cli_token. 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.
create_cli_token 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 →