Подробная инфа о любом entity: пользователе/чате/канале/боте.
AI agents call get_chat_info 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 information about Telegram entities (users, chats, channels, bots) without performing any writes, deletions, or executing external operations. It is a pure read operation with minimal blast radius if misused—the worst case being exposure of publicly or semi-publicly accessible chat metadata.
From the tool's definition Tool name 'get_chat_info' and description 'Подробная инфа о любом entity: пользователе/чате/канале/боте' (Detailed info about any entity: user/chat/channel/bot) indicate retrieval of chat metadata with no modification or execution capability.
Attacks that exploit this kind of access
Подробная инфа о любом entity: пользователе/чате/канале/боте. 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_chat_info: 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_chat_info 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_chat_info 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_chat_info. 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_chat_info 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 →