Счётчики диалогов по типам — без payload, 1 запрос.
AI agents call dialog_stats 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 aggregate statistics about dialogs (message counts, dialog types, etc.) without modifying, deleting, or executing any operations. It is a read-only query operation that gathers information about the user's Telegram dialogs. The explicit mention of 'без payload' (without payload) and the nature of counter retrieval confirms no data modification occurs.
From the tool's definition Tool name 'dialog_stats' and description 'Счётчики диалогов по типам — без payload, 1 запрос' (Dialog counters by types — without payload, 1 request) indicate retrieval of statistics/counters from existing dialogs with no side effects.
Attacks that exploit this kind of access
Счётчики диалогов по типам — без payload, 1 запрос. 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 dialog_stats: 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.
dialog_stats 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 dialog_stats 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 dialog_stats. 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.
dialog_stats 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 →