botbell_send · BotBell MCP Server MCP: Risk & Policy

WHAT IT DOES

What botbell_send does on BotBell MCP Server

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

WHY IT NEEDS A POLICY

Why botbell_send needs a policy

This tool creates new notification records and modifies the user's device state by delivering messages. While it does not delete, execute code, or move money, it does create data (notifications) and can be misused to spam, harass, or socially engineer the user. The impact is reversible (notifications can be dismissed) and localized to notifications rather than core user data, warranting 'medium' severity.

From the tool's definition The tool 'botbell_send' sends a push notification to the user — this is a write operation that creates/modifies the state of notifications in the user's device and the BotBell app.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

botbell_send Rate-limited

botbell_send 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": {
    "botbell_send": {
      "limits": [
        {
          "counter": "botbell_send_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 BotBell MCP Server, so you can run agents against it safely.

FAQ

Questions about botbell_send

What does the botbell_send tool do? +

Send a push notification to the user. It is categorised as a Write tool in the BotBell MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on botbell_send? +

Register the BotBell MCP Server MCP server in PolicyLayer and add a rule for botbell_send: 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 BotBell MCP Server. Nothing to install.

What risk level is botbell_send? +

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

Can I rate-limit botbell_send? +

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

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

botbell_send is provided by the BotBell MCP Server MCP server (qq418716640/botbell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.