# Claude IPC

> Use this tool when you need to enable secure inter-process communication between multiple AI instances running on the same machine, particularly in WSL environments. It solves problems of data sharing and coordination between AI models, such as Claude and Gemini, by providing a message broker for registration, queuing, broadcasting, and file sharing. With features like automatic message forwarding and rate limiting, it is ideal for multi-AI workflows, collaborative problem-solving, and building integrated AI systems that require seamless communication and data exchange.

Canonical page: https://skillsregistry.net/skills/jdez427-claude-ipc  
JSON: https://api.skillsregistry.net/v1/skills/jdez427-claude-ipc

## Description

This MCP server enables secure inter-process communication between multiple AI instances (Claude, Gemini, etc.) running on the same machine, particularly designed for WSL environments. Built with Python using TCP sockets and session-based authentication, it provides a message broker that handles registration, message queuing, broadcasting, file sharing, and command output sharing between AI instances, with features like automatic message forwarding during instance renames, large message file storage, and rate limiting. The implementation includes both MCP tools for Claude integration and standalone Python scripts for other AI models, making it valuable for coordinating multi-AI workflows, collaborative problem-solving scenarios, and building AI systems that need to communicate and share data across different instances without manual intervention.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/jdez427-claude-ipc)
- **Repository:** <https://github.com/jdez427/claude-ipc-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jdez427-claude-ipc"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jdez427-claude-ipc` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jdez427-claude-ipc/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt