AI agents call rcs_events to retrieve information from Seven without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool consumes and manages incoming event data from RCS messaging (delivery confirmations, read status, typing indicators). This is a read operation: it retrieves event information without creating, modifying, or deleting data. The low severity reflects minimal blast radius—misuse would only expose message metadata and event logs, not enable unauthorized messaging or financial transactions.
From the tool's definition Tool is designed to 'handle RCS events' such as 'delivery reports, read receipts, IS_TYPING' — these are passive event status updates and notifications that the tool retrieves or processes, with no capability to send messages, modify accounts, or perform…
Attacks that exploit this kind of access
Handle RCS events (delivery reports, read receipts, IS_TYPING, etc.). It is categorised as a Read tool in the Seven MCP Server, which means it retrieves data without modifying state.
Register the Seven MCP server in PolicyLayer and add a rule for rcs_events: 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 Seven. Nothing to install.
rcs_events 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 rcs_events 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 rcs_events. 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.
rcs_events is provided by the Seven MCP server (seven-io/seven-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 →