send_message_by_filter · Codex Peers MCP: Risk & Policy

WHAT IT DOES

What send_message_by_filter does on Codex Peers MCP

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

WHY IT NEEDS A POLICY

Why send_message_by_filter needs a policy

This tool writes/sends a message to another Codex session peer. It performs a Write action (creating and delivering a message) rather than just reading. The severity is medium because AI agents could use it to coordinate or influence other AI sessions on the same machine, which carries moderate risk of cross-session manipulation or unintended side effects, but it is reversible and does not delete data or execute…

From the tool's definition 'send a message' and 'Resolve a target peer by repo/cwd/summary filters' — the tool creates and delivers a message to another peer session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_message_by_filter Rate-limited

send_message_by_filter 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": {
    "send_message_by_filter": {
      "limits": [
        {
          "counter": "send_message_by_filter_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 Codex Peers MCP, so you can run agents against it safely.

FAQ

Questions about send_message_by_filter

What does the send_message_by_filter tool do? +

Resolve a target peer by repo/cwd/summary filters and send a message without manually copying peer ids. It is categorised as a Write tool in the Codex Peers MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_message_by_filter? +

Register the Codex Peers MCP server in PolicyLayer and add a rule for send_message_by_filter: 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 Codex Peers MCP. Nothing to install.

What risk level is send_message_by_filter? +

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

Can I rate-limit send_message_by_filter? +

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

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

send_message_by_filter is provided by the Codex Peers MCP server (jscianna/codex-peers-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.