react_message · Claudegram MCP: Risk & Policy

WHAT IT DOES

What react_message does on Claudegram

AI agents use react_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 react_message needs a policy

This tool adds a reaction to a message, which is a reversible write operation. It modifies message state (adds/changes a reaction) but does not delete data or have financial implications. Misuse could send unwanted reactions to arbitrary messages, hence medium severity.

From the tool's definition react_message — 'Поставить реакцию-эмодзи на сообщение' (Set an emoji reaction on a message)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

react_message Rate-limited

react_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": {
    "react_message": {
      "limits": [
        {
          "counter": "react_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 react_message

What does the react_message tool do? +

Поставить реакцию-эмодзи на сообщение. 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 react_message? +

Register the Claudegram MCP server in PolicyLayer and add a rule for react_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 react_message? +

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

Can I rate-limit react_message? +

Yes. Add a rate_limit block to the react_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 react_message completely? +

Set action: deny in the PolicyLayer policy for react_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 react_message? +

react_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.