AI agents call current_tracking to retrieve information from Early MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the status of an active timer without modifying, deleting, or executing external operations. It is a simple read operation that queries the current state of time tracking. No data is created, modified, or deleted. The blast radius of misuse is minimal—an attacker would only gain visibility into what is currently being tracked, not the ability to manipulate time records or financial data.
From the tool's definition Tool name is 'current_tracking' and description states 'Get the currently running tracking entry, if any.' The verb 'Get' indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Get the currently running tracking entry, if any. It is categorised as a Read tool in the Early MCP MCP Server, which means it retrieves data without modifying state.
Register the Early MCP server in PolicyLayer and add a rule for current_tracking: 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 Early MCP. Nothing to install.
current_tracking 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 current_tracking 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 current_tracking. 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.
current_tracking is provided by the Early MCP server (sakebomb/early_mcp). 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 →