AI agents call sync to retrieve information from ATMcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads events from a cursor position and optionally waits for new events via long-polling. This is a purely read operation with no side effects — it fetches state/event data for synchronization purposes. No writes, executions, or deletions are implied.
From the tool's definition 'Catch up on events since a cursor' and 'long-poll' indicate this tool only retrieves/queries event data without modifying state
Attacks that exploit this kind of access
Catch up on events since a cursor. If nothing new and wait_ms > 0, long-poll up to. It is categorised as a Read tool in the ATMcp MCP Server, which means it retrieves data without modifying state.
Register the AT MCP server in PolicyLayer and add a rule for sync: 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 ATMcp. Nothing to install.
sync 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 sync 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 sync. 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.
sync is provided by the AT MCP server (midcheck/atmcp). 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 →