block_user · Claudegram MCP: Risk & Policy

WHAT IT DOES

What block_user does on Claudegram

AI agents use block_user 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 block_user needs a policy

Blocking a user modifies account/relationship state by preventing the user from sending messages. This is a reversible action (users can be unblocked), so it falls under Write rather than Destructive. However, it has a high severity because an AI agent misusing this tool could block arbitrary users, causing significant social/communication harm at scale across a personal Telegram account.

From the tool's definition Заблокировать пользователя — он не сможет писать. (Block a user — they will not be able to write.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

block_user Rate-limited

block_user 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": {
    "block_user": {
      "limits": [
        {
          "counter": "block_user_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 block_user

What does the block_user tool do? +

Заблокировать пользователя — он не сможет писать. 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 block_user? +

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

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

Can I rate-limit block_user? +

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

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

block_user 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.