Get full message body. Auto-marks as read.
AI agents call read_message to retrieve information from Claude Sync without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves message content ('Get full message body') with a benign side effect of marking the message as read. There is no data modification, deletion, execution of commands, or financial impact. The marking as read is a standard, reversible state change typical of message systems. Classified as Read because the primary function is data retrieval.
From the tool's definition Tool name is 'read_message' and description states 'Get full message body. Auto-marks as read.' - this is a retrieval operation with only status-marking side effects.
Attacks that exploit this kind of access
Get full message body. Auto-marks as read. It is categorised as a Read tool in the Claude Sync MCP Server, which means it retrieves data without modifying state.
Register the Claude Sync MCP server in PolicyLayer and add a rule for read_message: 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 Claude Sync. Nothing to install.
read_message 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 read_message 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 read_message. 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.
read_message is provided by the Claude Sync MCP server (the-firmament/claude-sync). 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 →