start_bot · Claudegram MCP: Risk & Policy

WHAT IT DOES

What start_bot does on Claudegram

AI agents invoke start_bot to trigger actions in Claudegram. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_bot needs a policy

This tool executes a command (/start) against an external Telegram bot with user-controlled parameters (deep-link). While not inherently destructive, it triggers external operations whose side effects are unpredictable and depend on the bot's code and the parameters passed. An AI agent could abuse this to trigger malicious bots, phishing flows, or unauthorized actions.

From the tool's definition Tool name 'start_bot' and description 'Start a bot (send /start) with deep-link parameter' indicates execution of a bot command with parameters that can trigger external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_bot Rate-limited

start_bot 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.

View as policy code

policy.json

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

RATE-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 start_bot

What does the start_bot tool do? +

Запустить бота (отправить /start) с deep-link параметром. It is categorised as a Execute tool in the Claudegram MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_bot? +

Register the Claudegram MCP server in PolicyLayer and add a rule for start_bot: 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 start_bot? +

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

Can I rate-limit start_bot? +

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

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

start_bot 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.