send-message

THE RISK

Medium Risk

Why send-message needs a policy

This tool creates new messages in Telegram chats, which is a reversible write operation. While not destructive (messages can be deleted), it modifies chat state and could be misused to spam users, send phishing content, or impersonate the bot owner. The high severity reflects the potential blast radius of an AI agent sending unsolicited or malicious messages to many users.

From the tool's definition Tool name 'send-message' and description 'Send message using a chat id' indicate the tool creates and transmits new messages to Telegram chats. The capability to send messages to arbitrary chat IDs constitutes data creation and modification of chat state.

Documented attack patterns abuse exactly the kind of access send-message gives an agent:

POLICY

How to control send-message

PolicyLayer is an MCP gateway — it sits between your AI agents and Telegram Bot MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send-message:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send-message": {
      "limits": [
        {
          "counter": "send-message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

send-message stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Telegram Bot MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Telegram Bot MCP Server tools

Destructive kick-chat-member Kick a user from a group, a supergroup or a channel. Provides detailed error information i Write un-ban-chat-member Use this method to unban a previously banned user in a supergroup or channel. The user wil Write send-photo Send photo with caption using a chat id. Automatically handles long captions that exceed T Write set-my-commands Use this method to change the list of the bot Write set-my-description Use this method to change the bot Write set-my-name Use this method to change the bot Write set-my-short-description Use this method to change the bot Read get-chat Use this method to get up-to-date information about the chat. Returns detailed chat inform

All 16 Telegram Bot MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about send-message

What does the send-message tool do? +

Send message using a chat id. Automatically splits long messages that exceed Telegram. It is categorised as a Write tool in the Telegram Bot MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send-message? +

Register the Telegram Bot MCP Server MCP server in PolicyLayer and add a rule for send-message: 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 Telegram Bot MCP Server. Nothing to install.

What risk level is send-message? +

send-message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send-message? +

Yes. Add a rate_limit block to the send-message 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.

How do I block send-message completely? +

Set action: deny in the PolicyLayer policy for send-message. 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.

What MCP server provides send-message? +

send-message is provided by the Telegram Bot MCP Server MCP server (siavashdelkhosh81/telegram-bot-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Telegram Bot MCP Server tool call.

Start from Telegram Bot MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →