Press an inline keyboard callback button on a message. Identify the button by (row, column) from its replyMarkup, or pass raw callback_data as base64. URL, switch-inline, game and 2FA-password buttons are rejected with a clear error. Returns the bot
AI agents invoke telegram-press-button to trigger actions in MCP-Telegram. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Pressing an inline button triggers external operations on a bot/service whose effects depend entirely on what the button does — could initiate purchases, confirmations, state changes, etc. The tool executes callback actions on the user's behalf via their personal Telegram account (userbot), giving it broad blast radius since the consequences vary unpredictably based on which button is pressed.
From the tool's definition Press an inline keyboard callback button on a message... Returns the bot
Documented attack patterns abuse exactly the kind of access telegram-press-button 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-press-button:
{
"version": "1",
"default": "deny",
"tools": {
"telegram-press-button": {
"limits": [
{
"counter": "telegram-press-button_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} telegram-press-button stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Press an inline keyboard callback button on a message. Identify the button by (row, column) from its replyMarkup, or pass raw callback_data as base64. URL, switch-inline, game and 2FA-password buttons are rejected with a clear error. Returns the bot. It is categorised as a Execute tool in the MCP-Telegram MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP-Telegram MCP server in PolicyLayer and add a rule for telegram-press-button: 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-press-button is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the telegram-press-button 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-press-button. 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-press-button 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.