# Tetrees MCP

Connects coding agents to Tetrees AI Packs (.taip) to discover tools, inspect verification reports, and quote task runs.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 298
- Author: TetreesEX
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/TetreesEX/TetreesAgent_EX
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/mcp/tetrees-mcp

## What it does

Tetrees MCP links desktop coding assistants to the Tetrees AI Packs ecosystem. It lets the agent query the catalog for `.taip` packages, review public Agent AVCP assessment reports, and inspect runtime profiles.

Model runs require a prior quote in Tetrees Points. This prevents surprise credit consumption. The integration also supports user-side client extensions like no-shell local processes, nested MCP servers, and HTTPS endpoints. Private credentials stay on the local machine.

Running via `npx` requires Node.js 20+ and an account token saved as `TETREES_TOKEN`. Without that token from `https://ex.tetrees.ai/en/account`, the MCP process fails to communicate with the remote API.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://ex.tetrees.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http tetrees-mcp https://ex.tetrees.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add tetrees-mcp --url https://ex.tetrees.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "tetrees-mcp": {
            "url": "https://ex.tetrees.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "tetrees-mcp": {
            "type": "http",
            "url": "https://ex.tetrees.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http tetrees-mcp https://ex.tetrees.ai/mcp
```

## When to use it
- search agent packages across the Tetrees AI Packs registry
- calculate point estimates before running model tasks
- integrate local no-shell skills and nested servers without sharing API keys
- review Agent AVCP verification reports prior to using third-party packages

## Example prompts
- Search Tetrees AI Packs for issue triage tools and show the public Agent AVCP score
- Quote a run for pack-id with an 8k token limit before starting execution
- List owned Tetrees packages and inspect the runtime profile for this pack

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md