AI agents use archive_chat 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.
Archiving is a write operation that modifies chat metadata/visibility state. It is reversible (chats can be unarchived), distinguishing it from destructive operations like delete_message or delete_contact which are irreversible. The blast radius is medium: an agent archiving all chats could disrupt user workflow and communication visibility, but the action can be undone.
From the tool's definition Tool description states 'Archive a chat' – archiving is a reversible modification action that changes chat state without deletion or irreversible data loss.
Attacks that exploit this kind of access
Archive a chat. 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 archive_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 Tgmcp. Nothing to install.
archive_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 archive_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 archive_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.
archive_chat 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 →