AI agents call subscribe_resource 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 establishes a subscription to receive notifications about resource changes. It retrieves notification data passively through polling. There are no side effects, state modifications, code execution, financial implications, or destructive operations. This is purely a Read operation that queries the state of resource changes.
From the tool's definition Tool description explicitly states it 'Subscribe to local MCP resource change notifications' and directs users to 'poll via get_resource_changes'.
Attacks that exploit this kind of access
Subscribe to local MCP resource change notifications (poll via get_resource_changes). 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 subscribe_resource: 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.
subscribe_resource 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 subscribe_resource 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 subscribe_resource. 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.
subscribe_resource 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 →