click_inline_button · Claudegram MCP: Risk & Policy

WHAT IT DOES

What click_inline_button does on Claudegram

AI agents invoke click_inline_button 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 click_inline_button needs a policy

Clicking an inline button on a Telegram bot can trigger arbitrary bot-side actions (payments, commands, state changes, external API calls). The effect is determined by the bot's logic, making this an Execute-category action with high severity since an AI agent could trigger unintended bot operations at scale.

From the tool's definition 'Нажать inline-кнопку' means 'Click an inline button under a bot message' — this triggers an external operation whose effects depend on the specific button/bot being interacted with.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

click_inline_button Rate-limited

click_inline_button 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": {
    "click_inline_button": {
      "limits": [
        {
          "counter": "click_inline_button_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 click_inline_button

What does the click_inline_button tool do? +

Нажать inline-кнопку под сообщением бота. 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 click_inline_button? +

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

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

Can I rate-limit click_inline_button? +

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

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

click_inline_button 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.