Создать invite-ссылку на чат/канал.
AI agents use export_chat_invite to create or update resources in Claudegram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claudegram environment.
This tool creates invite links for Telegram chats/channels, which is a reversible modification of chat sharing configuration. It doesn't delete data (not Destructive), doesn't execute arbitrary code (not Execute), and doesn't involve financial transactions (not Financial). The ability to generate invite links could be misused to share access to private chats without owner consent, warranting medium severity.
From the tool's definition Tool name 'export_chat_invite' and description 'Создать invite-ссылку на чат/канал' (Create invite-link for chat/channel) indicates creation of shareable links that modify chat accessibility settings.
Attacks that exploit this kind of access
Создать invite-ссылку на чат/канал. It is categorised as a Write tool in the Claudegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claudegram MCP server in PolicyLayer and add a rule for export_chat_invite: 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.
export_chat_invite 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 export_chat_invite 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 export_chat_invite. 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.
export_chat_invite 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 →