send_poll · Claudegram MCP: Risk & Policy

WHAT IT DOES

What send_poll does on Claudegram

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

WHY IT NEEDS A POLICY

Why send_poll needs a policy

send_poll creates a new poll in a Telegram chat, which is a reversible write operation. It modifies chat state by adding a message artifact. Severity is high because an agent could spam polls, manipulate voting behavior, or misuse polls for social engineering in the user's personal Telegram account. Not Execute because it doesn't directly run arbitrary code or scripts—it sends a structured message type.

From the tool's definition Tool name 'send_poll' in a Telegram interaction MCP server, part of a 120-tool suite for 'messaging, media, chat management'. Sibling tools include messaging operations like 'add_contact', 'archive_dialog', and 'click_inline_button'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_poll Rate-limited

send_poll 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_poll": {
      "limits": [
        {
          "counter": "send_poll_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 Claudegram, so you can run agents against it safely.

FAQ

Questions about send_poll

What does the send_poll tool do? +

send_poll. It is categorised as a Write tool in the Claudegram 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_poll? +

Register the Claudegram MCP server in PolicyLayer and add a rule for send_poll: 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 Claudegram. Nothing to install.

What risk level is send_poll? +

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

Can I rate-limit send_poll? +

Yes. Add a rate_limit block to the send_poll 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_poll completely? +

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

send_poll is provided by the Claudegram MCP server (sanjar-x/claudegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.