AI agents call get_banned_users to retrieve information from Tgmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing information about banned users in a group or channel. It performs a read operation without modifying, deleting, or executing any actions. While it accesses security-sensitive information (banned user lists), the tool itself does not change state or enable harmful actions directly—it merely retrieves data.
From the tool's definition Tool name is 'get_banned_users' and description states 'Get all banned users in a group or channel' — the verb 'get' and 'retrieve' operation indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Get all banned users in a group or channel. It is categorised as a Read tool in the Tgmcp MCP Server, which means it retrieves data without modifying state.
Register the Tg MCP server in PolicyLayer and add a rule for get_banned_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 Tgmcp. Nothing to install.
get_banned_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 get_banned_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 get_banned_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.
get_banned_users is provided by the Tg MCP server (oevortex/tgmcp). 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 →