AI agents use create_group to create or update resources in Tgmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tgmcp environment.
This tool creates new groups and adds users, which are reversible Write operations. While it modifies account state and could enable spam or abuse through group creation, it does not delete data (Destructive), execute arbitrary code (Execute), involve financial transactions (Financial), or irreversibly alter data.
From the tool's definition Tool name is 'create_group' and description states 'Create a new group or supergroup and add users.' This is a reversible creation operation that modifies the state of the Telegram account by creating new entities and modifying group membership.
Attacks that exploit this kind of access
Create a new group or supergroup and add users. It is categorised as a Write tool in the Tgmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tg MCP server in PolicyLayer and add a rule for create_group: 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.
create_group is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_group 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 create_group. 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.
create_group 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 →