get_task_logs
AI agents call get_task_logs 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 queries and retrieves log data from Airflow task executions, which is a read-only operation with no side effects. However, severity is medium rather than low because logs may contain sensitive information (credentials, API keys, business logic details, PII) that could be exposed if an agent overshares or mishandles the retrieved data.
From the tool's definition Tool name 'get_task_logs' retrieves task execution logs from MWAA/Airflow. No description provided, but the name and server context (workflow execution monitoring) indicate a read operation.
Attacks that exploit this kind of access
get_task_logs. 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_task_logs: 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_task_logs 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_task_logs 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_task_logs. 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_task_logs 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 →