AI agents call list_active_files 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 and lists files associated with active tasks. It performs a read-only query operation ('return all files') without creating, modifying, deleting, or executing anything. The phrase 'linked to in-progress tasks' confirms it is accessing existing data rather than making changes. No side effects or destructive actions are indicated.
From the tool's definition Tool name 'list_active_files' and description 'Return all files linked to in-progress tasks' indicate a query/retrieval operation with no modification or deletion of data.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Return all files linked to in-progress tasks across all agents — the bird. 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_active_files: 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_active_files 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_active_files 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_active_files. 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_active_files 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 →