AI agents call query_tasks_by_workflow_state 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 is a data retrieval operation that searches for tasks matching workflow state criteria. It has no side effects, does not execute code, and does not modify any data. It falls clearly into the Read category with low severity since querying task metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name contains 'query' and description states 'Query tasks by local workflow state' - it retrieves/queries task data without modifying it. The verb 'preserving' indicates no side effects.
Attacks that exploit this kind of access
Query tasks by local workflow state while preserving canonical task statuses. 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 query_tasks_by_workflow_state: 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.
query_tasks_by_workflow_state 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 query_tasks_by_workflow_state 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 query_tasks_by_workflow_state. 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.
query_tasks_by_workflow_state 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 →