텔레그램 채팅에 연락처(전화번호+이름)를 전송합니다.
AI agents use telegram_send_contact to create or update resources in Telegram MCP Server & Channel Monitor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Telegram MCP Server & Channel Monitor environment.
Sending a contact to a chat is a write operation that creates new message content in a reversible manner. It does not execute arbitrary code, delete data permanently, or move financial resources.
From the tool's definition Tool name 'telegram_send_contact' and description indicating it sends contact information (phone number + name) to Telegram chats. This creates/adds new data (contact message) to a chat, which is reversible via deletion.
Attacks that exploit this kind of access
텔레그램 채팅에 연락처(전화번호+이름)를 전송합니다. It is categorised as a Write tool in the Telegram MCP Server & Channel Monitor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Telegram MCP Server & Channel Monitor MCP server in PolicyLayer and add a rule for telegram_send_contact: 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 Telegram MCP Server & Channel Monitor. Nothing to install.
telegram_send_contact 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 telegram_send_contact 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 telegram_send_contact. 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.
telegram_send_contact is provided by the Telegram MCP Server & Channel Monitor MCP server (ruchiayeon/telegram-mcp). 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 →