Сменить @username аккаунта (пустая строка — снять username).
AI agents use update_username 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.
The tool creates or modifies user account data (username/handle) reversibly. While it affects public identity, the change can be undone by setting a new username or clearing it. This is a Write operation rather than Destructive because the action is reversible and doesn't permanently delete or overwrite irretrievable data.
From the tool's definition Tool description states 'Сменить @username аккаунта' (Change account @username) with option to clear it (empty string). This modifies account metadata reversibly.
Attacks that exploit this kind of access
Сменить @username аккаунта (пустая строка — снять username). 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 update_username: 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.
update_username 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 update_username 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 update_username. 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.
update_username 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 →