// SCAN REPORT

Tgfmcp

14 tools. 9 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

9 can modify or destroy data

5 read-only

14 tools total

Community server · catalogue entry verified 29/06/2026

How to control Tgfmcp ↓

TOOL MAP

What Tgfmcp exposes to your agents

Read (5) Write / Execute (8) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Tgfmcp tools

Destructive · High telegram_delete_message Delete a Telegram message using explicit chat and message IDs. Write · Medium telegram_edit_message Edit a previously sent Telegram text message using explicit chat and message IDs. Write · Medium telegram_forward_message Forward an existing Telegram message to another chat using explicit source chat and message IDs. Write · Medium telegram_react_to_message Add an emoji reaction to an existing Telegram message using explicit chat and message IDs.

9 of Tgfmcp's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Tgfmcp

PolicyLayer is an MCP gateway — it sits between your AI agents and Tgfmcp, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "telegram_delete_message": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "telegram_edit_message": {
    "limits": [
      {
        "counter": "telegram_edit_message_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "telegram_get_chat": {
    "limits": [
      {
        "counter": "telegram_get_chat_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Tgfmcp — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TGFMCP →

Instant setup, no code required.

FULL CATALOGUE

All 14 Tgfmcp tools

DESTRUCTIVE 1 tools

Destructive telegram_delete_message Delete a Telegram message using explicit chat and message IDs.

WRITE 8 tools

Write telegram_edit_message Edit a previously sent Telegram text message using explicit chat and message IDs. Write telegram_forward_message Forward an existing Telegram message to another chat using explicit source chat and message IDs. Write telegram_react_to_message Add an emoji reaction to an existing Telegram message using explicit chat and message IDs. Write telegram_reply_to_message Send a reply to an existing Telegram message using explicit chat and message IDs. Write telegram_send_media_from_base64 Send media to Telegram using a base64 payload with MIME type and optional filename/caption. Write telegram_send_media_from_path Send a local file to Telegram by file path. Write telegram_send_message Send a plain text message to a Telegram chat, group, or channel. Write telegram_send_typing Show the typing indicator in a target Telegram chat.

READ 5 tools

Read telegram_get_chat Get details for a Telegram chat by numeric ID or username. Read telegram_get_chat_administrators List administrators for a Telegram group, supergroup, or channel. Read telegram_get_me Return the current session details for the connected Telegram bot. Read telegram_get_status Return the current connection status for this Telegram bot session. Read telegram_lookup_chat Resolve a Telegram chat or channel by numeric ID or username.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Tgfmcp

Can an AI agent delete data through the Tgf MCP server? +

Yes. The Tgfmcp server exposes 1 destructive tools including telegram_delete_message. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Tgfmcp? +

The Tgfmcp server has 8 write tools including telegram_edit_message, telegram_forward_message, telegram_react_to_message. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Tgfmcp.

How many tools does the Tgf MCP server expose? +

14 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on Tgfmcp? +

Register the Tgf MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Tgfmcp tool call.

Deterministic rules across all 14 Tgfmcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TGFMCP →

Instant setup, no code required.

14 Tgfmcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.