AI agents call get_task to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves task information without any side effects. It falls squarely into the Read category as it queries and returns data. The blast radius of misuse is minimal—an agent could view task data it shouldn't access, but cannot modify or execute anything. Severity is low as this is a simple informational read operation.
From the tool's definition Tool name is 'get_task' and description states it retrieves 'compact task details' with an option for 'full multi-line view'. The verb 'Get' and the retrieval-focused language indicate pure data querying with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get compact task details by default. Pass detail=full for the full multi-line view. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for get_task: 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 Todos. Nothing to install.
get_task 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 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. 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 is provided by the Todos MCP server (@hasna/todos). 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 →