AI agents call poll_local_snapshots 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.
The tool retrieves snapshot data based on a cursor filter. The word 'return' indicates data retrieval, and 'poll' in this context means query/check status. There is no indication of data modification, deletion, execution, or financial impact. This is a straightforward Read operation with minimal risk.
From the tool's definition Tool description states it 'Poll local snapshots and return only resources with cursors newer than the supplied ISO cursor' — purely a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Poll local snapshots and return only resources with cursors newer than the supplied ISO cursor. 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 poll_local_snapshots: 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.
poll_local_snapshots 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 poll_local_snapshots 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 poll_local_snapshots. 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.
poll_local_snapshots 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 →