Личные чаты с юзерами (без ботов).
AI agents call list_pm_users 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 and queries existing personal chat data from a Telegram account. It performs no modifications, deletions, or external operations—it only reads private message metadata. Severity is medium rather than low because the data retrieved includes personal communications, which could expose sensitive conversation metadata if misused by an AI agent.
From the tool's definition Tool name 'list_pm_users' and description 'Personal chats with users (without bots)' indicate retrieval/listing of private messages and user data without modification.
Attacks that exploit this kind of access
Личные чаты с юзерами (без ботов). 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 list_pm_users: 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.
list_pm_users 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_pm_users 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_pm_users. 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_pm_users 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 →