forward_message · Claudegram MCP: Risk & Policy

WHAT IT DOES

What forward_message does on Claudegram

AI agents use forward_message 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 forward_message needs a policy

Forwarding messages creates new messages in a target chat, which is a write operation. It is reversible in principle (messages can be deleted), but the blast radius is high because an AI agent could forward sensitive or private messages to unintended recipients, causing privacy breaches at scale across 120+ available messaging tools.

From the tool's definition 'Переслать сообщения из одного чата в другой' (Forward messages from one chat to another)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

forward_message Rate-limited

forward_message 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": {
    "forward_message": {
      "limits": [
        {
          "counter": "forward_message_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 forward_message

What does the forward_message tool do? +

Переслать сообщения из одного чата в другой. 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 forward_message? +

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

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

Can I rate-limit forward_message? +

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

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

forward_message 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.