Список отложенных сообщений в чате (которые ещё не отправлены).
AI agents call get_scheduled_messages to retrieve information from Claudegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_scheduled_messages retrieves data about scheduled (unsent) messages without modifying, deleting, or executing them. This is a pure read operation with minimal blast radius—an AI agent listing scheduled messages cannot cause harm beyond potential information disclosure of the user's own draft messages.
From the tool's definition Tool description translates to 'List of delayed messages in a chat (which have not yet been sent).' The verb is 'list' and the action is retrieval only—no modification, deletion, or execution of side effects.
Attacks that exploit this kind of access
Список отложенных сообщений в чате (которые ещё не отправлены). It is categorised as a Read tool in the Claudegram MCP Server, which means it retrieves data without modifying state.
Register the Claudegram MCP server in PolicyLayer and add a rule for get_scheduled_messages: 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 Claudegram. Nothing to install.
get_scheduled_messages 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 get_scheduled_messages 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 get_scheduled_messages. 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.
get_scheduled_messages is provided by the Claudegram MCP server (sanjar-x/claudegram). 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 →