AI agents call list_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.
This tool performs a read-only operation to retrieve and enumerate snapshot data from local resources. It has no side effects, does not modify data, execute code, delete resources, or commit financial transactions. It is clearly a query/list operation typical of the Read category.
From the tool's definition Tool name contains 'list' and description uses 'List' as the action verb. The description explicitly states it retrieves/queries 'stable local snapshot resources' with no mention of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
List stable local snapshot resources for projects, tasks, plans, runs, dependencies, events, and evidence. 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 list_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.
list_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 list_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 list_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.
list_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 →