list_dags
AI agents call list_dags 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.
The tool name 'list_dags' clearly indicates it lists or queries DAGs (Directed Acyclic Graphs) without modifying them. While the description is uninformative, the naming convention and context from sibling tools strongly suggest this is a read-only operation that retrieves/enumerates workflow definitions. There is no indication it creates, modifies, deletes, executes, or commits any operations.
From the tool's definition Tool name is 'list_dags' which indicates retrieval/listing functionality. Description is empty, but the tool name follows the pattern of read-only list operations common in query interfaces.
Attacks that exploit this kind of access
list_dags. 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 list_dags: 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.
list_dags 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_dags 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_dags. 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_dags 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 →