Получить текущие privacy-настройки для указанного ключа.
AI agents call get_privacy 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.
This tool retrieves or queries privacy settings data with no side effects. It performs a read-only operation to fetch current privacy configuration. The lack of write, delete, or execution capabilities, combined with the 'get_' prefix indicating a retrieval operation, clearly places it in the Read category with low severity.
From the tool's definition Tool name 'get_privacy' and description 'Получить текущие privacy-настройки для указанного ключа' (Get current privacy settings for the specified key) indicate a retrieval operation that queries existing privacy configuration without modification.
Attacks that exploit this kind of access
Получить текущие privacy-настройки для указанного ключа. 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_privacy: 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_privacy 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_privacy 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_privacy. 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_privacy 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 →