send_gif · Tg MCP: Risk & Policy

WHAT IT DOES

What send_gif does on Tgmcp

AI agents use send_gif to create or update resources in Tgmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tgmcp environment.

WHY IT NEEDS A POLICY

Why send_gif needs a policy

send_gif creates a new message object in a Telegram chat, which is a reversible modification of chat state. While it could be misused to spam or harass (medium severity), it does not permanently destroy data, execute arbitrary code, move money, or have the blast radius of destructive or execute-category tools.

From the tool's definition Tool description: 'Send a GIF to a chat' — this is a send/message operation that creates new data (a message) in a chat.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_gif Rate-limited

send_gif 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_gif": {
      "limits": [
        {
          "counter": "send_gif_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Tgmcp, so you can run agents against it safely.

FAQ

Questions about send_gif

What does the send_gif tool do? +

Send a GIF to a chat by Telegram GIF document ID (not a file path). It is categorised as a Write tool in the Tgmcp 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_gif? +

Register the Tg MCP server in PolicyLayer and add a rule for send_gif: 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 Tgmcp. Nothing to install.

What risk level is send_gif? +

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

Can I rate-limit send_gif? +

Yes. Add a rate_limit block to the send_gif 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_gif completely? +

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

send_gif is provided by the Tg MCP server (oevortex/tgmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.