# Cross-Claude

> Use this tool when you need to enable communication between multiple AI instances, whether on the same machine or across different platforms, to facilitate collaboration and data sharing. Cross-Claude solves problems of AI isolation by providing a message bus with named channels, threaded conversations, and shared data storage. It accepts various inputs through its REST API and supports multiple transport modes, making it suitable for use cases requiring cross-model and cross-machine collaboration.

Canonical page: https://skillsregistry.net/skills/rblank9-cross-claude  
JSON: https://api.skillsregistry.net/v1/skills/rblank9-cross-claude

## Description

Cross-Claude provides a message bus that lets multiple AI instances communicate with each other through named channels, threaded conversations, and shared data storage. It supports both local mode using stdio transport with SQLite for single-machine multi-terminal setups, and remote mode using Streamable HTTP with PostgreSQL for cross-machine and cross-model collaboration. The REST API enables non-MCP clients like ChatGPT Custom GPTs to participate alongside native MCP clients, making it a bridge between different AI platforms.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rblank9-cross-claude)
- **Repository:** <https://github.com/rblank9/cross-claude-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": "rblank9-cross-claude"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rblank9-cross-claude` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rblank9-cross-claude/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