AI agents use unarchive_chat to create or update resources in Telegram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Telegram environment.
This tool modifies chat metadata (archived/unarchived state) reversibly. It does not read data without side effects (Read), execute arbitrary code (Execute), permanently delete data (Destructive), or involve financial transactions (Financial). The blast radius is limited to chat organization state—misuse could restore unwanted chats to visibility but causes no data loss.
From the tool's definition Tool name 'unarchive_chat' and description 'Unarchive a chat' indicate a reversible state modification operation.
Attacks that exploit this kind of access
Unarchive a chat. It is categorised as a Write tool in the Telegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Telegram MCP server in PolicyLayer and add a rule for unarchive_chat: 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. Nothing to install.
unarchive_chat 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 unarchive_chat 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 unarchive_chat. 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.
unarchive_chat is provided by the Telegram MCP server (vovavindar/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 →