# teammate-mcp

> Use this tool when you need to facilitate collaboration between AI models, such as Claude Code and OpenAI Codex, to enable them to ask each other questions and share information seamlessly. It solves the problem of isolated AI model interactions by providing a simple interface for models to communicate through iTerm panes. With teammate-mcp, you can easily integrate AI models without requiring daemons or per-project configuration, making it ideal for projects that involve multiple AI models working together.

Canonical page: https://skillsregistry.net/skills/jonghklee-teammate-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jonghklee-teammate-mcp

## Description

Enables Claude Code and OpenAI Codex to ask each other questions through iTerm panes, with no daemon or per-project configuration.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/sj3fo7e3yg)
- **Repository:** <https://github.com/jonghklee/teammate-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": "jonghklee-teammate-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jonghklee-teammate-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jonghklee-teammate-mcp/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