telegram_call

THE RISK

High Risk

Why telegram_call needs a policy

This tool is a generic executor for any Telegram Bot API method. Because it can invoke destructive actions (delete messages, ban users), write actions (send messages, upload files), and potentially irreversible operations, it spans multiple severity categories. The most severe applicable is Execute (with critical severity) since it provides unrestricted access to the full Bot API surface.

From the tool's definition 'Call any Telegram Bot API method' — arbitrary execution of any of 169 Telegram Bot API methods, including sending messages, managing chats, banning users, deleting messages, and more.

Documented attack patterns abuse exactly the kind of access telegram_call gives an agent:

POLICY

How to control telegram_call

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "telegram_call": {
      "limits": [
        {
          "counter": "telegram_call_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

telegram_call 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.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Telegram Api tools

Write mark_trail Write an entry to the TRAIL content log. Use to explicitly record content actions. Read download_file Download a file from Telegram by file_id. Saves locally and returns the path. Use after re Read get_trail Query the TRAIL content log. Check what content was posted, failed, or skipped across pipe Read get_trail_stats Get summary statistics from the TRAIL content log. Read telegram_find Search Telegram Bot API methods by keyword. Returns matching methods with their parameters

All 6 Telegram Api tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Telegram Api → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about telegram_call

What does the telegram_call tool do? +

Call any Telegram Bot API method. Use telegram_find first to discover method names and required parameters. It is categorised as a Execute tool in the Telegram Api MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on telegram_call? +

Register the Telegram Api MCP server in PolicyLayer and add a rule for telegram_call: 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 Api. Nothing to install.

What risk level is telegram_call? +

telegram_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit telegram_call? +

Yes. Add a rate_limit block to the telegram_call 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 telegram_call completely? +

Set action: deny in the PolicyLayer policy for telegram_call. 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 telegram_call? +

telegram_call is provided by the Telegram Api MCP server (timoncool/telegram-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Telegram Api tool call.

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

CHECK YOUR STACK →