post_message · Claude ↔ Codex MCP Relay MCP: Risk & Policy

WHAT IT DOES

What post_message does on Claude ↔ Codex MCP Relay

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

WHY IT NEEDS A POLICY

Why post_message needs a policy

This tool creates/writes data (messages) reversibly. Messages can typically be edited or deleted, so it's not destructive. It doesn't execute code, access financial systems, or retrieve data. The medium severity reflects that misuse could spam channels, post misleading information, or disrupt collaborative workflows, but the impact is limited to message data which remains recoverable.

From the tool's definition Tool description states 'Post a message into a target inbox (channel)' — this creates new message data in a channel.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

post_message Rate-limited

post_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": {
    "post_message": {
      "limits": [
        {
          "counter": "post_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 Claude ↔ Codex MCP Relay, so you can run agents against it safely.

FAQ

Questions about post_message

What does the post_message tool do? +

Post a message into a target inbox (channel). It is categorised as a Write tool in the Claude ↔ Codex MCP Relay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on post_message? +

Register the Claude ↔ Codex MCP Relay MCP server in PolicyLayer and add a rule for post_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 Claude ↔ Codex MCP Relay. Nothing to install.

What risk level is post_message? +

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

Can I rate-limit post_message? +

Yes. Add a rate_limit block to the post_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 post_message completely? +

Set action: deny in the PolicyLayer policy for post_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 post_message? +

post_message is provided by the Claude ↔ Codex MCP Relay MCP server (wiresharks/claudecodex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.