AI agents call get_label to retrieve information from Todoist without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about a label without creating, modifying, or deleting any data. It is a simple read-only query operation. The low severity reflects that querying label metadata poses minimal risk even if invoked inappropriately by an AI agent.
From the tool's definition Tool name is 'get_label' and description states 'Get a specific label by ID' — a pure retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get a specific label by ID. It is categorised as a Read tool in the Todoist MCP Server, which means it retrieves data without modifying state.
Register the Todoist MCP server in PolicyLayer and add a rule for get_label: 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 Todoist. Nothing to install.
get_label 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_label 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_label. 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_label is provided by the Todoist MCP server (stevengonsalvez/mcp-todoist). 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 →