AI agents call list_dialogs to retrieve information from Telegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list_' prefix and position among read-only tools (get_messages, list_folders, get_chat_info) strongly indicate this retrieves or enumerates Telegram dialogs/conversations. No side effects, no data modification, and no external operations. The empty description slightly reduces confidence, but the naming convention and sibling tools make the classification reliable.
From the tool's definition Tool named 'list_dialogs' with no description. Based on the sibling tools context (list_chats, get_messages, list_folders), this follows the 'list' pattern which retrieves data without modification.
Attacks that exploit this kind of access
list_dialogs. It is categorised as a Read tool in the Telegram MCP Server, which means it retrieves data without modifying state.
Register the Telegram MCP server in PolicyLayer and add a rule for list_dialogs: 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 Telegram. Nothing to install.
list_dialogs 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 list_dialogs 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 list_dialogs. 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.
list_dialogs is provided by the Telegram MCP server (vovavindar/telegram-mcp). 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 →