Список несохранённых черновиков по всем чатам.
AI agents call get_drafts to retrieve information from Claudegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that fetches draft message data. It has no side effects, does not modify state, and presents minimal security risk. The low severity reflects that exposed drafts could reveal user communication patterns or sensitive information, but the tool itself performs only data retrieval.
From the tool's definition get_drafts retrieves unsaved drafts across all chats ("Список несохранённых черновиков по всем чатам" translates to "List of unsaved drafts across all chats"). The tool only queries/retrieves data without modifying, deleting, or executing actions.
Attacks that exploit this kind of access
Список несохранённых черновиков по всем чатам. It is categorised as a Read tool in the Claudegram MCP Server, which means it retrieves data without modifying state.
Register the Claudegram MCP server in PolicyLayer and add a rule for get_drafts: 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.
get_drafts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_drafts 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 get_drafts. 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.
get_drafts 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 →