AI agents use create_channel 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 channels/supergroups, which are reversible (channels can be deleted). It modifies the Telegram account state but does not irreversibly destroy data or cause financial impact. The blast radius is moderate—an AI agent could spam channels or create unwanted groups, but the damage is containable through deletion.
From the tool's definition Tool description states 'Create a new channel or supergroup' — a create action that generates new entities in Telegram.
Attacks that exploit this kind of access
Create a new channel or supergroup. 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_channel: 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_channel 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_channel 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_channel. 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_channel 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 →