unban_participant · Claudegram MCP: Risk & Policy

WHAT IT DOES

What unban_participant does on Claudegram

AI agents use unban_participant 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 unban_participant needs a policy

Unbanning a participant is a reversible write operation that modifies a user's access/status in a chat. It can be undone by re-banning. Severity is medium because misuse could restore access to previously removed bad actors.

From the tool's definition "Снять бан с участника" (Remove ban from participant) — reverses a ban, modifying participant access state

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unban_participant Rate-limited

unban_participant 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": {
    "unban_participant": {
      "limits": [
        {
          "counter": "unban_participant_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 unban_participant

What does the unban_participant tool do? +

Снять бан с участника. 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 unban_participant? +

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

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

Can I rate-limit unban_participant? +

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

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

unban_participant 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.