AI agents call telegram-get-drafts to retrieve information from MCP-Telegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While this is fundamentally a Read operation (querying existing data), the severity is elevated to 'high' because: (1) the server operates as a userbot with full access to the user's personal Telegram account, (2) drafts may contain sensitive, private, or unfinished communications intended to remain hidden, and (3) an AI agent with access to this tool could exfiltrate private drafts without the user's explicit…
From the tool's definition 'Get all saved message drafts across chats' — retrieves draft messages without modifying or deleting them. This is a query/retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access telegram-get-drafts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Telegram, and nothing reaches the server without passing your rules. This is the rule we recommend for telegram-get-drafts:
{
"version": "1",
"default": "deny",
"tools": {
"telegram-get-drafts": {}
}
} telegram-get-drafts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all saved message drafts across chats. It is categorised as a Read tool in the MCP-Telegram MCP Server, which means it retrieves data without modifying state.
Register the MCP-Telegram MCP server in PolicyLayer and add a rule for telegram-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 MCP-Telegram. Nothing to install.
telegram-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 telegram-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 telegram-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.
telegram-get-drafts is provided by the MCP-Telegram MCP server (mcp-telegram/mcp-telegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-Telegram, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
181 MCP-Telegram tools catalogued and risk-classified — across an index of 43,000+ MCP servers.