Переместить диалог в архив (folder=1).
AI agents use archive_dialog 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 modifies the organizational state of a Telegram dialog by moving it to an archive folder. It is reversible (dialogs can be unarchived), making it a Write operation rather than Destructive. The severity is medium because while it affects user data organization, it does not delete information, expose sensitive data, or perform financial operations.
From the tool's definition 'Переместить диалог в архив' (Move dialog to archive); folder=1 parameter indicates structural modification of chat/dialog state.
Attacks that exploit this kind of access
Переместить диалог в архив (folder=1). 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 archive_dialog: 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.
archive_dialog 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_dialog 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_dialog. 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_dialog 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 →