List the inline/reply keyboard buttons on a Telegram message with their (row, col) indices, type (e.g. KeyboardButtonCallback, KeyboardButtonUrl), label and type-specific fields (callback data as base64, url, switchQuery, userId, copyText, etc). Helper for telegram-press-button — call this first ...
AI agents call telegram-get-message-buttons 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.
This tool only queries and displays metadata about buttons present on a message. It retrieves button labels, types, indices, and associated data (callback data, URLs, etc.) without modifying state, executing commands, or triggering actions. The severity is low because button information is non-sensitive metadata; misuse causes no data loss, financial impact, or irreversible changes.
From the tool's definition Tool description states it 'List[s] the inline/reply keyboard buttons' and 'Returns markup type' — pure information retrieval with no side effects. Explicitly described as a 'Helper' for discovering button indices before action, not performing actions itself.
Documented attack patterns abuse exactly the kind of access telegram-get-message-buttons 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-message-buttons:
{
"version": "1",
"default": "deny",
"tools": {
"telegram-get-message-buttons": {}
}
}telegram-get-message-buttons 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.
List the inline/reply keyboard buttons on a Telegram message with their (row, col) indices, type (e.g. KeyboardButtonCallback, KeyboardButtonUrl), label and type-specific fields (callback data as base64, url, switchQuery, userId, copyText, etc). Helper for telegram-press-button — call this first to discover indices and filter by type before pressing. Returns markupType=. 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-message-buttons: 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-message-buttons 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-message-buttons 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-message-buttons. 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-message-buttons 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.