Конфигурация клиента (флаги фич, premium-лимиты, gifts и т.д.).
AI agents call get_app_config 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 application configuration settings such as feature flags, premium limits, and gift settings. It performs a read-only query of client configuration state with no capability to modify data, trigger external operations, or cause destructive changes. The blast radius of misuse is minimal—an agent could only view configuration details, not alter system behavior or data.
From the tool's definition Tool name 'get_app_config' and description 'Client configuration (feature flags, premium limits, gifts, etc.)' indicate retrieval of configuration data without modification or side effects.
Attacks that exploit this kind of access
Конфигурация клиента (флаги фич, premium-лимиты, gifts и т.д.). 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_app_config: 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_app_config 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_app_config 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_app_config. 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_app_config 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 →